It was day 18 into a month of daily mindfulness. I was running late to my 10:10 a.m. class, but I needed coffee before I tried to digest Marketing Strategy. The kettle finished and I poured the boiling water over a pile of instant coffee powder. I went to grab the mug for my first sip and I tipped it.

Scalding hot coffee raced across my desk and splashed everywhere. Normally, I would deem the day a failure, leave without coffee and mope around in a grouchy mood. This time was different. I took a deep breath, calmly cleaned up the mess and made myself a fresh cup of coffee.

According to mindful.org, about 95% of our behavior runs on autopilot. After learning this, I had refused to let the statistic apply to me.

So for the month of March, I practiced mindfulness everyday. Mindfulness can be any activity where you are fully present in whatever it is that you are doing. I practiced yoga, conscious eating, walking and meditation.

This practice was inspired by my 11:15 a.m. Mindful Communications class, taught by Aime Knight, Ph.D., associate professor of communication and media studies. Knight has been practicing mindfulness for eight years and debuted the class Mindful Communications this semester.

No matter what is happening, whether its a pandemic, or youre having a disagreement with someone or something tragic happens, [my students] have tools to be able to manage their mental state, Knight said.

In the class, we learned different ways to practice mindfulness, how to implement mindfulness in your everyday life and how to cultivate mindfulness in ourselves and our communities. Knight believed the class to be beneficial for students because of the control that mindfulness allows them to have over their emotions.

Jack McCaul 22, another student enrolled in Knights class, has been practicing mindfulness since sophomore year of high school when his dad introduced him to the teachings of zen Buddhist monk, Thich Nhat Khan.

McCaul said mindfulness changed his life by shifting his autopilot lifestyle to a more intentional mindset, where he could focus on the people and things he truly cared about.

Mindfulness allowed me to really love my friends and understand why I should tell people that I love them, how to treat people and how precious life is in general, McCaul said.

At the start of my 30 day journey, I found it hard to carve out a long chunk of time to sit on a pillow and meditate. I had put so much pressure on myself to sit through lengthy meditations, which left me feeling anxious as I constantly wondered how much time was left. It wasnt until day 12 when I realized that even a three minute meditation can help bring me back to the present moment.

By day 18 I felt like I had full control of my emotions.

Jennifer Fisher, therapist for St. Joes Counseling and Psychological Services (CAPS) and organizer of the Mindful Morning meditation series on Zoom every Wednesday, was not surprised when I told her my coffee anecdote. She said students often feel rushed in the mornings and carry that rushed feeling with them throughout the day.

Practicing mindfulness in the morning for students would be a really good skill to develop because it would help set themselves up and get into a healthy routine, Fisher said.

I agreed, as it was at the moment I spilled my coffee when I realized the true benefits of maintaining a mindfulness practice.

I could have easily reacted negatively, allowed my emotions to take control and subconsciously ruined my entire day. However, through the awareness of my thoughts and utilizing the breathing techniques I learned in Knights class, I was able to pause and choose how I wanted to react.

After concluding my 30 days of daily practice, I felt that the everyday worries that cluttered my mind were cleared. My emotions were more stable, I was more observant of my surroundings and more compassionate toward my friends.

I hope to keep mindfulness a part of my daily routine, as the practice only becomes stronger with time.

Continue reading here:

The art of mindfulness The Hawk Newspaper - The Hawk

To be truly useful, dronesthat is, autonomous flying vehicleswill need to learn to navigate real-world weather and wind conditions.

Right now, drones are either flown under controlled conditions, with no wind, or are operated by humans using remote controls. Drones have been taught to fly in formation in the open skies, but those flights are usually conducted under ideal conditions and circumstances.

However, for drones to autonomously perform necessary but quotidian tasks, such as delivering packages or airlifting injured drivers from a traffic accident, drones must be able to adapt to wind conditions in real timerolling with the punches, meteorologically speaking.

To face this challenge, a team of engineers from Caltech has developed Neural-Fly, a deep-learning method that can help drones cope with new and unknown wind conditions in real time just by updating a few key parameters.

Neural-Fly is described in a study published on May 4 in Science Robotics. The corresponding author is Soon-Jo Chung, Bren Professor of Aerospace and Control and Dynamical Systems and Jet Propulsion Laboratory Research Scientist. Caltech graduate students Michael O'Connell (MS '18) and Guanya Shi are the co-first authors.

Neural-Fly was tested at Caltech's Center for Autonomous Systems and Technologies (CAST) using its Real Weather Wind Tunnel, a custom 10-foot-by-10-foot array of more than 1,200 tiny computer-controlled fans that allows engineers to simulate everything from a light gust to a gale.

"The issue is that the direct and specific effect of various wind conditions on aircraft dynamics, performance, and stability cannot be accurately characterized as a simple mathematical model," Chung says. "Rather than try to qualify and quantify each and every effect of turbulent and unpredictable wind conditions we often experience in air travel, we instead employ a combined approach of deep learning and adaptive control that allows the aircraft to learn from previous experiences and adapt to new conditions on the fly with stability and robustness guarantees."

Time-lapse photo shows a drone equipped with Neural-Fly maintaining a figure-eight course amid stiff winds at Caltech's Real Weather Wind Tunnel.

O'Connell adds: "We have many different models derived from fluid mechanics, but achieving the right model fidelity and tuning that model for each vehicle, wind condition, and operating mode is challenging. On the other hand, existing machine learning methods require huge amounts of data to train yet do not match state-of-the-art flight performance achieved using classical physics-based methods. Moreover, adapting an entire deep neural network in real time is a huge, if not currently impossible task."

Neural-Fly, the researchers say, gets around these challenges by using a so-called separation strategy, through which only a few parameters of the neural network must be updated in real time.

"This is achieved with our new meta-learning algorithm, which pre-trains the neural network so that only these key parameters need to be updated to effectively capture the changing environment," Shi says.

After obtaining as little as 12 minutes of flying data, autonomous quadrotor drones equipped with Neural-Fly learn how to respond to strong winds so well that their performance significantly improved (as measured by their ability to precisely follow a flight path). The error rate following that flight path is around 2.5 times to 4 times smaller compared to the current state of the art drones equipped with similar adaptive control algorithms that identify and respond to aerodynamic effects but without deep neural networks.

Out of the lab and into the sky: engineers test Neural-Fly in the open air on Caltech's campus

Neural-Fly, which was developed in collaboration with Caltech's Yisong Yue, Professor of Computing and Mathematical Sciences, and Anima Anandkumar, Bren Professor of Computing and Mathematical Sciences, is based on earlier systems known as Neural-Lander and Neural-Swarm. Neural-Lander also used a deep-learning method to track the position and speed of the drone as it landed and modify its landing trajectory and rotor speed to compensate for the rotors' backwash from the ground and achieve the smoothest possible landing; Neural-Swarm taught drones to fly autonomously in close proximity to each other.

Though landing might seem more complex than flying, Neural-Fly, unlike the earlier systems, can learn in real time. As such, it can respond to changes in wind on the fly, and it does not require tweaking after the fact. Neural-Fly performed as well in flight tests conducted outside the CAST facility as it did in the wind tunnel. Further, the team has shown that flight data gathered by an individual drone can be transferred to another drone, building a pool of knowledge for autonomous vehicles.

(L to R) Guanya Shi, Soon-Jo Chung, and Michael O'Connell, in front of the wall of fans at Caltech's Center for Autonomous Systems and Technologies

At the CAST Real Weather Wind Tunnel, test drones were tasked with flying in a pre-described figure-eight pattern while they were blasted with winds up to 12.1 meters per secondroughly 27 miles per hour, or a six on the Beaufort scale of wind speeds. This is classified as a "strong breeze" in which it would be difficult to use an umbrella. It ranks just below a "moderate gale," in which it would be difficult to move and whole trees would be swaying. This wind speed is twice as fast as the speeds encountered by the drone during neural network training, which suggests Neural-Fly could extrapolate and generalize well to unseen and harsher weather.

The drones were equipped with a standard, off-the-shelf flight control computer that is commonly used by the drone research and hobbyist community. Neural-Fly was implemented in an onboard Raspberry Pi 4 computer that is the size of a credit card and retails for around $20.

The Science Robotics paper is titled "Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds." Coauthors include Anandkumar and Yue, as well as Xichen Shi (PhD '21), and former Caltech postdoc Kamyar Azizzadenesheli, now an assistant professor of computer science at Purdue University. Funding for this research came from the Defense Advanced Research Projects Agency (DARPA) and Raytheon.

The rest is here:

Rapid Adaptation of Deep Learning Teaches Drones to Survive Any Weather - Caltech

This article is part of Demystifying AI, a series of posts that (try to) disambiguate the jargon and myths surrounding AI. (In partnership with Paperspace)

In recent years, the transformer model has become one of the main highlights of advances in deep learning and deep neural networks. It is mainly used for advanced applications in natural language processing. Google is using it to enhance its search engine results. OpenAI has used transformers to create its famous GPT-2 and GPT-3 models.

Since its debut in 2017, the transformer architecture has evolved and branched out into many different variants, expanding beyond language tasks into other areas. They have been used for time series forecasting. They are the key innovation behind AlphaFold, DeepMinds protein structure prediction model. Codex, OpenAIs source codegeneration model, is based on transformers. More recently, transformers have found their way into computer vision, where they are slowly replacing convolutional neural networks (CNN) in many complicated tasks.

Researchers are still exploring ways to improve transformers and use them in new applications. Here is a brief explainer about what makes transformers exciting and how they work.

The classic feed-forward neural network is not designed to keep track of sequential data and maps each input into an output. This works for tasks such as classifying images but fails on sequential data such as text. A machine learning model that processes text must not only compute every word but also take into consideration how words come in sequences and relate to each other. The meaning of words can change depending on other words that come before and after them in the sentence.

Before transformers, recurrent neural networks (RNN) were the go-to solution for natural language processing. When provided with a sequence of words, an RNN processes the first word and feeds back the result into the layer that processes the next word. This enables it to keep track of the entire sentence instead of processing each word separately.

Recurrent neural nets had disadvantages that limited their usefulness. First, they were very slow. Since they had to process data sequentially, they could not take advantage of parallel computing hardware and graphics processing units (GPU) in training and inference. Second, they could not handle long sequences of text. As the RNN got deeper into a text excerpt, the effects of the first words of the sentence gradually faded. This problem, known as vanishing gradients, was problematic when two linked words were very far apart in the text. And third, they only captured the relations between a word and the words that came before it. In reality, the meaning of words depends on the words that come both before and after them.

Long short-term memory (LSTM) networks, the successor to RNNs, were able to solve the vanishing gradients problem to some degree and were able to handle larger sequences of text. But LSTMs were even slower to train than RNNs and still couldnt take full advantage of parallel computing. They still relied on the serial processing of text sequences.

Transformers, introduced in the 2017 paper Attention Is All You Need, made two key contributions. First, they made it possible to process entire sequences in parallel, making it possible to scale the speed and capacity of sequential deep learning models to unprecedented rates. And second, they introduced attention mechanisms that made it possible to track the relations between words across very long text sequences in both forward and reverse directions.

Before we discuss how the transformer model works, it is worth discussing the types of problems that sequential neural networks solve.

A vector to sequence model takes a single input, such as an image, and produces a sequence of data, such as a description.

A sequence to vector model takes a sequence as input, such as a product review or a social media post, and outputs a single value, such as a sentiment score.

A sequence to sequence model takes a sequence as input, such as an English sentence, and outputs another sequence, such as the French translation of the sentence.

Despite their differences, all these types of models have one thing in common. They learn representations. The job of a neural network is to transform one type of data into another. During training, the hidden layers of the neural network (the layers that stand between the input and output) tune their parameters in a way that best represents the features of the input data type and maps it to the output.

The original transformer was designed as a sequence-to-sequence (seq2seq) model for machine translation (of course, seq2seq models are not limited to translation tasks). It is composed of an encoder module that compresses an input string from the source language into a vector that represents the words and their relations to each other. The decoder module transforms the encoded vector into a string of text in the destination language.

The input text must be processed and transformed into a unified format before being fed to the transformer. First, the text goes through a tokenizer, which breaks it down into chunks of characters that can be processed separately. The tokenization algorithm can depend on the application. In most cases, every word and punctuation mark roughly counts as one token. Some suffixes and prefixes count as separate tokens (e.g., ize, ly, and pre). The tokenizer produces a list of numbers that represent the token IDs of the input text.

The tokens are then converted into word embeddings. A word embedding is a vector that tries to capture the value of words in a multi-dimensional space. For example, the words cat and dog can have similar values across some dimensions because they are both used in sentences that are about animals and house pets. However, cat is closer to lion than wolf across some other dimension that separates felines from canids. Similarly, Paris and London might be close to each other because they are both cities. However, London is closer to England and Paris to France on a dimension that separates countries. Word embeddings usually have hundreds of dimensions.

Word embeddings are created by embedding models, which are trained separately from the transformer. There are several pre-trained embedding models that are used for language tasks.

Once the sentence is transformed into a list of word embeddings, it is fed into the transformers encoder module. Unlike RNN and LSTM models, the transformer does not receive one input at a time. It can receive an entire sentences worth of embedding values and process them in parallel. This makes transformers more compute-efficient than their predecessors and also enables them to examine the context of the text in both forward and backward sequences.

To preserve the sequential nature of the words in the sentence, the transformer applies positional encoding, which basically means that it modifies the values of each embedding vector to represent its location in the text.

Next, the input is passed to the first encoder block, which processes it through an attention layer. The attention layer tries to capture the relations between the words in the sentence. For example, consider the sentence The big black cat crossed the road after it dropped a bottle on its side. Here, the model must associate it with cat and its with bottle. Accordingly, it should establish other associations such as big and cat or crossed and cat. Otherwise put, the attention layer receives a list of word embeddings that represent the values of individual words and produces a list of vectors that represent both individual words and their relations to each other. The attention layer contains multiple attention heads, each of which can capture different kinds of relations between words.

The output of the attention layer is fed to a feed-forward neural network that transforms it into a vector representation and sends it to the next attention layer. Transformers contain several blocks of attention and feed-forward layers to gradually capture more complicated relationships.

The task of the decoder module is to translate the encoders attention vector into the output data (e.g., the translated version of the input text). During the training phase, the decoder has access both to the attention vector produced by the encoder and the expected outcome (e.g., the translated string).

The decoder uses the same tokenization, word embedding, and attention mechanism to process the expected outcome and create attention vectors. It then passes this attention vector and the attention layer in the encoder module, which establishes relations between the input and output values. In the translation application, this is the part where the words from the source and destination languages are mapped to each other. Like the encoder module, the decoder attention vector is passed through a feed-forward layer. Its result is then mapped to a very large vector which is the size of the target data (in the case of language translation, this can span across tens of thousands of words).

During training, the transformer is provided with a very large corpus of paired examples (e.g., English sentences and their corresponding French translations). The encoder module receives and processes the full input string. The decoder, however, receives a masked version of the output string, one word at a time, and tries to establish the mappings between the encoded attention vector and the expected outcome. The encoder tries to predict the next word and makes corrections based on the difference between its output and the expected outcome. This feedback enables the transformer to modify the parameters of the encoder and decoder and gradually create the right mappings between the input and output languages.

The more training data and parameters the transformer has, the more capacity it gains to maintain coherence and consistency across long sequences of text.

In the machine translation example that we examined above, the encoder module of the transformer learned the relations between English words and sentences, and the decoder learns the mappings between English and French.

But not all transformer applications require both the encoder and decoder module. For example, the GPT family of large language models uses stacks of decoder modules to generate text. BERT, another variation of the transformer model developed by researchers at Google, only uses encoder modules.

The advantage of some of these architectures is that they can be trained through self-supervised learning or unsupervised methods. BERT, for example, does much of its training by taking large corpora of unlabeled text, masking parts of it, and trying to predict the missing parts. It then tunes its parameters based on how much its predictions were close to or far from the actual data. By continuously going through this process, BERT captures the statistical relations between different words in different contexts. After this pretraining phase, BERT can be finetuned for a downstream task such as question answering, text summarization, or sentiment analysis by training it on a small number of labeled examples.

Using unsupervised and self-supervised pretraining reduces the manual effort required to annotate training data.

A lot more can be said about transformers and the new applications they are unlocking, which is out of the scope of this article. Researchers are still finding ways to squeeze more out of transformers.

Transformers have also created discussions about language understanding and artificial general intelligence. What is clear is that transformers, like other neural networks, are statistical models that capture regularities in data in clever and complicated ways. They do not understand language in the way that humans do. But they are exciting and useful nonetheless and have a lot to offer.

This article was originally written by Ben Dickson and published by Ben Dickson onTechTalks, a publication that examines trends in technology, how they affect the way we live and do business, and the problems they solve. But we also discuss the evil side of technology, the darker implications of new tech, and what we need to look out for. You can read the original articlehere.

Read more:

Whats the transformer machine learning model? And why should you care? - The Next Web

COLUMBIA, Md.--(BUSINESS WIRE)--BigBear.ai (NYSE: BBAI), a leader in AI-powered analytics and cyber engineering solutions, announced company executives are embarking on a thought-leadership campaign across multiple global industry events. The campaign will emphasize how the companys advancements in AI technologies will impact the federal and commercial markets in the coming months.

At these events, BigBear.ai leaders will highlight the capabilities of BigBear.ais newly acquired company, ProModel Corporation, the importance of defining responsible AI usage, and how federal and commercial organizations leverage AI and ML.

The events BigBear.ai is scheduled to address include:

CTMA Partners Meeting May 3-5, 2022: Virginia Beach, VA

Due to the rapid deployment and advancement of sensor technologies, artificial intelligence, and data science, the Department of Defense has turned to a more predictive-based approach to maintaining technology assets. The agencys recently revamped condition-based maintenance plus (CBM+) policy will accelerate the adoption, integration, and use of these emerging technologies while shifting its strategic approach from largely reactive maintenance to proactive maintenance. Participating as part of a panel session to address this trend, BigBear.ai Senior Vice President of Analytics Carl Napoletano will highlight ProModels commercial capabilities and ProModel Government Services legacy capabilities in the federal space.

DIA Future Technologies Symposium May 11-12, 2022: Virtual Event

BigBear.ais Senior Vice President of Analytics, Frank Porcelli, will brief the DIA community about BigBear.ais AI-powered solutions at this virtual presentation. After providing a high-level overview and demonstration of the companys AI products (Observe, Orient, and Dominate), Frank will also offer insights into how AI technologies are being leveraged in the federal sector.

Conference on Governance of Emerging Technologies and Science May 19-20, 2022: Phoenix, Arizona

Newly appointed BigBear.ai General Counsel Carolyn Blankenship will attend the ninth edition of Arizona States annual conference, which examines how to create sustainable governance solutions that address new technologies legal, regulatory, and policy ramifications. During her presentation, Carolyn will detail the importance of Intellectual Property (IP) law in AI and the responsible use of AI and other emerging technologies. Prior to starting as General Counsel, Carolyn organized and led Thomson Reuters cross-functional team that outlined the organizations first set of Data Ethics Principles.

Automotive Innovation Forum May 24-25, 2022: Munich, Germany

ProModel was among the select few organizations invited to attend Autodesks The Automotive Innovation Forum 2022. This premier industry event celebrates new automotive plant design and manufacturing technology solutions. Michael Jolicoeur of ProModel, Director of the Autodesk Business Division, will headline a panel at the conference and highlight the latest industry trends in automotive factory design and automation.

DAX 2022 June 4, 2022: University of Maryland, Baltimore County, Baltimore, Maryland

Three BigBear.ai experts - Zach Casper, Senior Director of Cyber; Leon Worthen, Manager of Strategic Operations; and Sammy Hamilton, Data Scientist/Engagement Engineer - will headline a panel discussion exploring the variety of ways AI and ML are deployed throughout the defense industry. The trio of experts will discuss how AI and ML solve pressing cybersecurity problems facing the Department of Defense and intelligence communities.

To connect with BigBear.ai at these events, send an email to events@bigbear.ai.

About BigBear.ai

BigBear.ai delivers AI-powered analytics and cyber engineering solutions to support mission-critical operations and decision-making in complex, real-world environments. BigBear.ais customers, which include the US Intelligence Community, Department of Defense, the US Federal Government, as well as customers in manufacturing, logistics, commercial space, and other sectors, rely on BigBear.ais solutions to see and shape their world through reliable, predictive insights and goal-oriented advice. Headquartered in Columbia, Maryland, BigBear.ai has additional locations in Virginia, Massachusetts, Michigan, and California. For more information, please visit: http://bigbear.ai/ and follow BigBear.ai on Twitter: @BigBearai.

Go here to read the rest:

BigBear.ai to Highlight Artificial Intelligence and Machine Learning Capabilities at Upcoming Industry Events - Business Wire

First airing in 2002, The Bachelor is a titan in the world of Reality TV and has kept its most loyal viewers hooked for a full 26 seasons. To the uninitiated, the show follows 30 female contestants as they battle for the heart of a lone male bachelor, who proposes to the winner.

The contest begins the moment the women step out of a limo to meet the lead on Night One which culminates in him handing the First Impression Rose to the lady with whom he had the most initial chemistry. Over eight drama-fuelled weeks, the contestants travel to romantic destinations for their dates. At the end of each week, the lead selects one or two women for a one-on-one date, while eliminating up to five from the competition.

As self-styled mega-fans of The Bachelor, Abigail Lee and her colleagues at the University of Chicagos unofficial Department of Reality TV Engineering have picked up on several recurring characteristics in the women who tend to make it further in the competition. Overall, younger, white contestants are far more likely to succeed, with just one 30-something and one woman of color winning the leads heart in The Bachelors 20-year history a long-standing source of controversy.

The researchers are less clear on how other factors affect the contestants chances of success, such as whether they receive the First Impression Rose or are selected earlier for their first one-on-one date. Hometown and career also seem to have an unpredictable influence, though contestants with questionable job descriptions like Dog Lover, Free Spirit, and Chicken Enthusiast have rarely made it far.

For Lees team, such a diverse array of contestant parameters makes the show ripe for analysis with machine learning. In their study, Lees team compiled a dataset of contestant parameters that included all 422 contestants who participated in seasons 11 through 25. The researchers obviously encountered some adversity, as they note that they consum[ed] multiple glasses of wine per night during data collection.

Despite this setback, they used the data to train machine learning algorithms whose aim was to predict how far a given contestant will progress through the competition given her characteristics. In searching for the best algorithm, the team tried neural networks, linear regression, and random forest classification.

While the teams neural network performed the best overall in predicting the parameters of the most successful contestants, all three models were consistent with each other. This allowed them to confidently predict the characteristics of a woman with the highest probability of progressing far through the contest: 26 years of age, white, from the Northwest, works as a dancer, received her first one-on-one date on week 6, and didnt receive the First Impression Rose.

Lees team laments that The Bachelors viewership has steadily declined over the past few seasons. They blame a variety of factors, including influencer contestants (who are more concerned with growing their online following than finding true love) and the production crew increasingly meddling in the shows storylines, such as the infamous Champagne-gate of season 24.

By drawing on the insights gathered through their analysis, which the authors emphasize was done in their free time, the researchers hope that The Bachelors producers could think of new ways to shake up its format, while improving chances for contestants across a more diverse range of backgrounds, ensuring the show remains an esteemed cultural institution for years to come.

Of course, as a consolation prize, theres always Bachelor in Paradise.

Go here to read the rest:

Machine learning predicts who will win "The Bachelor" - Big Think

Terms like machine learning, artificial intelligence and deep learning have all become science buzzwords in recent years. But can these technologies be applied to saving lives?

The answer to that is a resounding yes. Future developments in health science may actually depend on integrating rapidly growing computing technologies and methods into medical practice.

Cosmos spoke with researchers from the University of Pittsburgh, in Pennsylvania, US, who have just published a paper in Radiology on the use of machine-learning techniques to analyse large data sets from brain trauma patients.

Co-lead author Shandong Wu, associate professor of radiology, is an authority on the use of machine learning in medicine. Machine-learning techniques have been around for several decades already, he explains. But it was in about 2012 that the so-called deep learning technique became mature. It attracted a lot of attention from the research field not only in medicine or healthcare, but in other domains, such as self-driving cars and robotics.

More on machine learning: Machine learning for cancer screening

So, what is deep learning? Its a kind of multi-layered, neural network-based model that is constantly mimicking how the human brain works to process a large set of data to learn or distill information, explains Wu.

The key to the increased maturity of machine-learning techniques in recent years is due to three interrelated developments, he says. These are the technical improvements in the algorithms of machine learning; the developments in the hardware being used, such as the improved graphical processing units; and the large volumes of digitised data readily available.

That data is key. Lots of it.

Get an update of science stories delivered straight to your inbox.

Machine-learning techniques use data to train the model to function better, and the more data the better. If you only have a small set of data, then you dont have a very good model, Wu explains. You may have very good questioning or good methodology, but youre not able to get a better model, because the model learns from lots of data.

Even though the available medical data is not as large as, say, social media data, there is still plenty to work with in the clinical domain.

Machine-learning models and algorithms can inform clinical decision-making, rapidly analysing massive amounts of data to identify patterns, says the papers other co-lead author, David Okonkwo.

Human beings can only process so much information. Machine learning permits orders of magnitude more information available than what an individual human can process, Okonkwo adds.

Okonkwo, a professor of neurological surgery, focuses on caring for patients with brain and spinal cord injuries, particularly those with traumatic brain injuries.

Our goal is to save lives, says Okonkwo. Machine-learning technologies will complement human experience and wisdom to maximise the decision-making for patients with serious injuries.

Even though today you dont see many examples, this will change the way that we practise medicine. We have very high hopes for machine learning and artificial intelligence to change the way that we treat many medical conditions from cancer, to making pregnancy safer, to solving the problems of COVID.

But important safeguards must be put in place. Okonkwo explains that institutions such as the US Food and Drugs Administration (FDA) must ensure that these new technologies are safe and effective before being used in real life-or-death scenarios.

Wu points out that the FDA has already approved about 150 artificial intelligence or machine learning-based tools. Tools need to be further developed or evaluated or used with physicians in the clinical settings to really examine their benefit for patient care, he says. The tools are not there to replace your physician, but to provide the tools and information to better inform physicians.

Read the original post:

Are machine-learning tools the future of healthcare? - Cosmos

A recent Forbes article highlighted the importance of increasing digital transformation in logistics and argued that many tech leaders should be adopting tech-forward thinking, execution and delivery in order to deliver with speed and keep a laser focus on the customer.

Since the COVID-19 pandemic, and even before, many logistics companies have been turning to technology to streamline their processes. For many, full digitization across the supply chain is the ultimate goal.

Despite many already taking steps toward advancing digitization efforts across supply chains, these processes are still fragmented due to all the moving parts and sectors of the industry such as integrators, forwarders and owners and the processes they each use.

Scale AI is partnering with companies in the logistics industry to better automate processes across the board and eliminate bottlenecks by simplifying integration, commercial invoicing, document processing and more through machine learning (ML).

ML is a subfield of artificial intelligence that allows applications to predict outcomes without having to be specifically programmed to do so.

The logistics industry has historically depended on lots of paperwork and this continues to be a bottleneck today. Many companies already use technology like optical character recognition (OCR) or template-based intelligent document processing (IDP). Both of these are substandard systems that can process raw data but require human key entry or engineers to make the data usable through creating and maintaining templates. This is costly and cannot be scaled easily. In a world where the end users are moving to getting results instantly and at a high quality, these methods take too long while providing low accuracy.

In the industry of logistics, it is a race to digitization to create a competitive edge, said Melisa Tokmak, General Manager of Document AI at Scale. Trying to use regular methods that require templates and heavily rely on manual key entry is not providing a good customer experience or accurate data quickly. This is making companies lose customer trust while missing out on the ROI machine learning can give them easily.

Scales mission is to accelerate the development of artificial intelligence.

Scale builds ML models and fine-tunes them for customers using a small sample of their documents. Its this method that removes the need for templates and allows all documents to be processed accurately within seconds, without human intervention. Tokmak believes that the logistics industry needs this type of technology now more than ever.

In the market right now, every consumer wants things faster, better and cheaper. It is essential for logistics companies to be able to serve the end user better, faster, and cheaper. That means meeting [the end users] where they are, Tokmak said. This change is already happening, so the question is how can you as a company do this faster than others so that you are early in building competitive edge?

Rather than simply learning where on a document to find a field, Scales ML models are capable of understanding the layout, hierarchy and meaning of every field of the document.

Document AI is also flexible to layout changes, table boundaries and other irregularities compared to that of traditional template-based systems.

Tokmak believes that because the current technology of OCR and IDP are not be getting the results needed by companies in the industry, the next step is partnering with companies, like Scale, to incorporate ML into their processes. After adopting this technology, Tokmak added that this can lead to companies knowing more about the market and getting visibility on global trade, which can lead to building new relevant tech.

Flexport, a recognizable name in the logistics industry and customer of Scale AI, is what is referred to as a digital forwarder. Digital forwarders are companies that digitally help customers through the whole shipment process without owning anything themselves. They function as a tech platform to make global trade easy, looking end to end to bring both sides of the marketplace together and ship more easily.

Before integrating an ML-solution, Flexport struggled to make more traditional means of data extraction like template-based and error-prone OCR work. Knowing its expertise was in logistics, Flexport partnered with Scale AI, an expert in ML, to reach its mission of making global trade easy and accessible for everyone more quickly, efficiently, and accurately. Now Flexport prides itself in its ability to process information more quickly and without human intervention.

As the supply chain crisis worsened, Flexports needs evolved. It became increasingly important for Flexport to extract estimated times of arrival (ETAs) to provide end users more visibility. Scales Document AI solution accommodated these changing requirements to extract additional fields in seconds and without templates from unstructured documents by retraining the ML models, providing more visibility on global trade at a time when many were struggling to get this level of insight at all.

According to a recent case study, Flexport has more than 95% accuracy with no templates and a less than 60-second turnaround since partnering with Scale.

Tokmak believes that in the future, companies ideally should have technology that functions as a knowledge graph a graph that represents things like objects, events, situations or concepts and illustrates the relationship among them to make business decisions accurately and fast. As it pertains to the logistics industry, Tokmak defines it as a global trade knowledge graph, which would provide information on where things are coming and going and how things are working, sensors all coming together to deliver users the best experience in the fastest way possible.

Realistically this will take time to fully incorporate and will require partnership from the logistics companies. The trick to enabling this future is starting with what will bring the best ROI and what will help your company find the easiest way to build new cutting edge products immediately, Tokmak said. There is a lot ML can achieve in this area without being very hard to adopt. Document processing is one of them a problem not solved with existing methods but can be solved with machine learning. It is a high value area with benefits of reducing costs, reducing delays, and bringing one source of truth for organizations within the company to operate with.

Tokmak stated that many in the industry have been disappointed with previous methods and were afraid to switch to ML for the same fear of disappointment but that has changed quickly in the last a few years. Companies do understand ML is different and they need to get on this train fast to actualize the gains form the technology.

It is so important to show people the power of ML and how every industry is getting reshaped with ML, Tokmak said. The first adopters are the winners.

The leading voices in supply chain are coming to Rogers, Arkansas, on May 9-10.

*limited term pricing available.

Continued here:

The race to digitization in logistics through machine learning - FreightWaves

Smolen, J. S., Aletaha, D. & McInnes, I. B. Rheumatoid arthritis. Lancet 388, 20232038 (2016).

CAS Article Google Scholar

Goekoop-Ruiterman, Y. P. & Huizinga, T. W. Rheumatoid arthritis: Can we achieve true drug-free remission in patients with RA?Nat. Rev. Rheumatol. 6, 6870 (2010).

Article Google Scholar

Aga, A. B. et al. Time trends in disease activity, response and remission rates in rheumatoid arthritis during the past decade: Results from the NOR-DMARD study 20002010. Ann. Rheum. Dis. 74, 381388 (2015).

CAS Article Google Scholar

van der Helm-van Mil, A. H. Risk estimation in rheumatoid arthritis: From bench to bedside. Nat. Rev. Rheumatol. 10, 171180 (2014).

Article Google Scholar

Ohrndorf, S. & Backhaus, M. Advances in sonographic scoring of rheumatoid arthritis. Ann. Rheum. Dis. 72, ii69ii75 (2013).

Article Google Scholar

Scir, C. A. et al. Ultrasonographic evaluation of joint involvement in early rheumatoid arthritis in clinical remission: Power Doppler signal predicts short-term relapse. Rheumatology (Oxford) 48, 10921097 (2009).

Article Google Scholar

Peluso, G. et al. Clinical and ultrasonographic remission determines different chances of relapse in early and long standing rheumatoid arthritis. Ann. Rheum. Dis. 70, 172175 (2011).

Article Google Scholar

Foltz, V. et al. Power Doppler ultrasound, but not low-field magnetic resonance imaging, predicts relapse and radiographic disease progression in rheumatoid arthritis patients with low levels of disease activity. Arthritis Rheum. 64, 6776 (2012).

Article Google Scholar

Iwamoto, T. et al. Prediction of relapse after discontinuation of biologic agents by ultrasonographic assessment in patients with rheumatoid arthritis in clinical remission: High predictive values of total gray-scale and power Doppler scores that represent residual synovial inflammation before discontinuation. Arthritis Care Res. 66, 15761581 (2014).

Article Google Scholar

Nguyen, H. et al. Prevalence of ultrasound-detected residual synovitis and risk of relapse and structural progression in rheumatoid arthritis patients in clinical remission: A systematic review and meta-analysis. Rheumatology (Oxford) 53, 21102118 (2014).

Article Google Scholar

Kawashiri, S. Y. et al. Ultrasound-detected bone erosion is a relapse risk factor after discontinuation of biologic disease-modifying antirheumatic drugs in patients with rheumatoid arthritis whose ultrasound power Doppler synovitis activity and clinical disease activity are well controlled. Arthritis Res. Ther. 19, 108 (2017).

Article Google Scholar

Matsuo, H. et al. Prediction of recurrence and remission using superb microvascular imaging in rheumatoid arthritis. J. Med. Ultrason. (2001)47, 131138 (2020).

Article Google Scholar

Matsuo, H. et al. Positive rate and prognostic significance of the superb microvascular imaging signal in joints of rheumatoid arthritis patients in remission with normal C-reactive protein levels and erythrocyte sedimentation rates. J. Med. Ultrason. (2001) 48, 353359 (2021).

Article Google Scholar

Ngiam, K. Y. & Khor, I. W. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 20, e262e273 (2019).

Article Google Scholar

Goecks, J., Jalili, V., Heiser, L. M. & Gray, J. W. How machine learning will transform biomedicine. Cell 181, 92101 (2020).

CAS Article Google Scholar

Kingsmore, K. M., Puglisi, C. E., Grammer, A. C. & Lipsky, P. E. An introduction to machine learning and analysis of its use in rheumatic diseases. Nat. Rev. Rheumatol. 17, 710730 (2021).

Article Google Scholar

Stafford, I. S. et al. A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases. NPJ Digit. Med. 3, 30 (2020).

CAS Article Google Scholar

Luque-Tvar, M. et al. Integrative clinical, molecular, and computational analysis identify novel biomarkers and differential profiles of anti-TNF response in rheumatoid arthritis. Front. Immunol. 12, 631662 (2021).

Article Google Scholar

Kalweit, M. et al. Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network. PLoSOne 16, e0252289 (2021).

CAS Article Google Scholar

Yoosuf, N. et al. Early prediction of clinical response to anti-TNF treatment using multi-omics and machine learning in rheumatoid arthritis. Rheumatology (Oxford) https://doi.org/10.1093/rheumatology/keab521 (2021).

Article Google Scholar

Vodencarevic, A. et al. Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs. Arthritis Res. Ther. 23, 67 (2021).

CAS Article Google Scholar

Koo, B. S. et al. Machine learning model for identifying important clinical features for predicting remission in patients with rheumatoid arthritis treated with biologics. Arthritis Res. Ther. 23, 178 (2021).

CAS Article Google Scholar

Johansson, F. D. et al. Predicting response to tocilizumab monotherapy in rheumatoid arthritis: A real-world data analysis using machine learning. J. Rheumatol. 48, 13641370 (2021).

CAS Article Google Scholar

van der Maaten, L. J. P. & Hinton, G. E. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 25792605 (2008).

MATH Google Scholar

Karlsson Sundbaum, J. et al. Methotrexate treatment in rheumatoid arthritis and elevated liver enzymes: A long-term follow-up of predictors, surveillance, and outcome in clinical practice. Int. J. Rheum. Dis. 22, 12261232 (2019).

CAS Article Google Scholar

Chen, Y., Yu, Z., Packham, J. C. & Mattey, D. L. Influence of adult height on rheumatoid arthritis: Association with disease activity, impairment of joint function and overall disability. PLoSOne 8, e64862 (2013).

ADS Article Google Scholar

Zhao, Y. et al. Ensemble learning predicts multiple sclerosis disease course in the SUMMIT study. NPJ Digit. Med. 3, 135 (2020).

Article Google Scholar

Morid, M. A., Lau, M. & Del Fiol, G. Predictive analytics for step-up therapy: Supervised or semi-supervised learning?. J. Biomed. Inform. 119, 103842 (2021).

Article Google Scholar

Fiorentino, M. C. et al. A deep-learning framework for metacarpal-head cartilage-thickness estimation in ultrasound rheumatological images. Comput. Biol. Med. 141, 105117 (2022).

Article Google Scholar

Rohrbach, J., Reinhard, T., Sick, T. & Drr, O. Bone erosion scoring for rheumatoid arthritis with deep convolutional neural networks. Comput. Electr. Eng. 78, 472481 (2019).

Article Google Scholar

Naredo, E. et al. Ultrasound joint inflammation in rheumatoid arthritis in clinical remission: How many and which joints should be assessed?. Arthritis Care Res. (Hoboken) 65, 512517 (2013).

Article Google Scholar

Backhaus, M. et al. Guidelines for musculoskeletal ultrasound in rheumatology. Ann. Rheum. Dis. 60, 641649 (2001).

CAS Article Google Scholar

Szkudlarek, M. et al. Interobserver agreement in ultrasonography of the finger and toe joints in rheumatoid arthritis. Arthritis Rheum. 48, 955962 (2003).

Article Google Scholar

Breiman, L. Random forests. Mach. Learn. 45, 532 (2001).

Article Google Scholar

Chen, T. & Carlos, G. XGBoost: A Scalable Tree Boosting System. KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785794. https://doi.org/10.1145/2939672.2939785 (2016).

Go here to read the rest:

Machine learning-based prediction of relapse in rheumatoid arthritis patients using data on ultrasound examination and blood test | Scientific Reports...

May 04, 2022(Nanowerk News) The biotech industry is constantly searching for the perfect mutation, where properties from different proteins are synthetically combined to achieve a desired effect. It may be necessary to develop new medicaments or enzymes that prolong the shelf-life of yogurt, break down plastics in the wild, or make washing powder effective at low water temperature.New research from DTU Compute and the Department of Computer Science at the University of Copenhagen (DIKU) can in the long term help the industry to accelerate the process. In the journal Nature Communications ("Learning meaningful representations of protein sequences"), the researchers explainhow a new way of using Machine Learning (ML) draws a map of proteins, that makes it possible to appoint a candidate list of the proteins that you need to examine more closely.The illustration depicts an example of the shortest path between two proteins, considering the geometry of the graphing. By defining distances in this way, it is possible to achieve biologically more precise and robust conclusions.(Image: W. Boomsma, N. S. Detlefsen, S. Hauberg)In recent years, we have started to use Machine Learning to form a picture of permitted mutations in proteins. The problem is, however, that you get different images depending on what method you use, and even if you train the same model several times, it can provide different answers about how the biology is related."In our work, we are looking at how to make this process more robust, and we are showing that you can extract significantly more biological information than you have previously been able to. This is an important step forward in order to be able to explore the mutation landscape in the hunt for proteins with special properties," says Postdoc Nicki Skafte Detlefsen from the Cognitive Systems section at DTU Compute.The map of the proteinsA protein is a chain of amino acids, and a mutation occurs when just one of these amino acids in the chain is replaced with another. As there are 20 natural amino acids, this means that the number of mutations increases so quickly that it is completely impossible to study them all. There are more possible mutations than there are atoms in the universe, even if you look at simple proteins. It is not possible to test everything in an experimental manner, so you must be selective about which proteins you want to try to produce synthetically.The researchers from DIKU and DTU Compute have used their ML model to generate a picture of how the proteins are linked. By presenting the model for many examples of protein sequences, it learns to draw a card with a dot for each protein so that closely related proteins are placed close to each other while distantly related proteins are placed far from each other.The ML model is based on mathematics and geometry developed to draw maps. Imagine that you must make a map of the globe. If you zoom in on Denmark, you can easily draw a map on a piece of paper that preserves the geography. But if you must draw the earth, mistakes will occur because you stretch the globe, so that the Arctic becomes a long country instead of a pole. So, on the map, the earth is distorted. For this reason, research in map-making has developed a lot of mathematics that describe the distortions and compensate for the distortions on the map.This is exactly the theory that DIKU and DTU Compute have been able to expand to cover their Machine Learning model (deep learning) for proteins. Because they have mastered the distortion on the map, they can also compensate for it."It enables us to talk about what a sensible distance target is between proteins that are closely related, and then we can suddenly measure it. In this way, we can draw a path through the map of the proteins that tells us which way we expect a protein to develop from to another i.e. mutated, since they are all related to evolution. In this way, the ML model can measure a distance between the proteins and draw optimal paths between promising proteins," says Wouter Boomsma, Associate Professor in the section for Machine Learning at DIKU.The researchers have tested the model on data from numerous proteins that are found in nature, where their structure is known, and they can see that the distance between proteins starts to correspond to the evolutionary development of the proteins, so that proteins that are close to each other evolutionally are placed close to each other."We are now able to put two proteins on the map and draw the curve between them. On the path between the two proteins are possible proteins, which have closely related properties. This is no guarantee, but it provides an opportunity to have a hypothesis about which proteins it could be that the biotech industry ought to test when new proteins are designed," says Sren Hauberg, professor in the Cognitive Systems section at DTU Compute.The unique collaboration between DTU Compute and DIKU was established through a new centre for Machine Learning in Life Sciences (MLLS), which started last year with the support of the Novo Nordisk Foundation. In the centre, researchers in artificial intelligence from both universities are working together to solve the fundamental problems in Machine Learning driven by important issues within the field of biology.The developed protein maps are part of a large-scale project that spans from basic research to industrial applications, e.g. in collaboration with Novozymes and Novo Nordisk.

Read the original:

New machine learning maps the potentials of proteins - Nanowerk

In machine learning procedures, making pipelines and extracting the best out of them is very crucial nowadays. We can understand that for a library to provide all the best services is difficult and even if they are providing such high-performing functions then they become heavy-weighted. Steppy is a library that tries to build an optimal pipeline but it is a lightweight library. In this article, we are going to discuss the steppy library and we will look at its implementation for a simple classification problem. The major points to be discussed in the article are listed below.

Lets start with introducing the steppy.

Steppy is an open-source library that can be used for performing data science experiments developed using the python language. The main reason behind developing this library is to make the procedure of experiments fast and reproducible. Along with this, it is a lightweight library and enables us to make high-performing machine learning pipelines. Developers of this library aim to make data science practitioners focused on the data side instead of focusing on issues regarding software development.

In the above section, we have discussed what steppy is and by looking at such points we can say this library can provide an environment where the experiments are fast, reproducible, and easy. With these capabilities, this library also helps in removing the difficulties with reproducibility and provides functions that can also be used by beginners. This library has two main abstractions using which we can make machine learning pipelines. Abstractions are as follows:

Any simple implementation can make the intentions behind the development of this library clear but before all this, we need to install this library that requires Python 3.5 or above in the environment. If we have it we can install this library using the following lines of codes:

After installation, we are ready to use steppy for data science experiments. Lets take a look at a basic implementation.

In this implementation of steppy, we will look at how we can use it for creating steps in a classification task.

In this article we are going to sklearn provided iris dataset that can be imported using the following lines of codes:

from sklearn.datasets import load_iris

Lets split the dataset into train and test.

One thing that we need to perform while using steppy is to put our data into dictionaries so that the step we are going to create can communicate with each other. We can do this in the following way:

Now we are ready to create steps.

In this article, we are going to fit a random forest algorithm to classify the iris data which means for steppy we are defining random forest as a transformer.

Here we have defined some of the functions that will help in initializing random forest, fitting and transforming data, and saving the parameters. Now we can fit the above transformer into the steps in the following ways:

Output:

Lets visualize the step.

step

Output:

Here we can see what are the step we have defined in the pipeline lets train the pipeline.

We can train our defined pipeline using the following lines of codes.

Output:

In the output, we can see that what is the step has been followed to train the pipeline. Lets evaluate the pipeline with test data.

Output:

Here we can see the testing procedure followed by the library. Lets check the accuracy of the model.

Output:

Here we can see the results are good and also if you will use it anytime you will find out how light this library is.

In this article, we have discussed the steppy library which is an open-source, lightweight and easy way to implement machine learning pipelines. Along with this, we also looked at the need for such a library and implementation to create steps in a pipeline using a steppy library.

Read this article:

How to create fast and reproducible machine learning models with steppy? - Analytics India Magazine