Collaborating Authors


Building a One-shot Learning Network with PyTorch


Deep learning has been quite popular for image recognition and classification tasks in recent years due to its high performances. However, traditional deep learning approaches usually require a large dataset for the model to be trained on to distinguish very few different classes, which is drastically different from how humans are able to learn from even very few examples. Few-shot or one-shot learning is a categorization problem that aims to classify objects given only a limited amount of samples, with the ultimate goal of creating a more human-like learning algorithm. In this article, we will dive into the deep learning approaches to solving the one-shot learning problem by using a special network structure: Siamese Network. We will build the network using PyTorch and test it on the Omniglot handwritten character dataset and performed several experiments to compare the results of different network structures and hyperparameters, using a one-shot learning evaluation metric.

How artificial intelligence is changing the GP-patient relationship - Pulse Today


'Alexa, what are the early signs of a stroke?' GPs may no longer be the first port of call for patients looking to understand their ailments. 'Dr Google' is already well established in patients' minds, and now they have a host of apps using artificial intelligence (AI), allowing them to input symptoms and receive a suggested diagnosis or advice without the need for human interaction. And policymakers are on board. Matt Hancock is the most tech-friendly health secretary ever, NHS England chief executive Simon Stevens wants England to lead the world in AI, and the prime minister last month announced £250m for a national AI lab to help cut waiting times and detect diseases earlier. Amazon even agreed a partnership with NHS England in July to allow people to access health information via its voice-activated assistant Alexa.

Ethics vs. compliance in AI -- FCW


The Defense Department is focused on implementing its ethics principles for artificial intelligence, especially when it comes to health-related data. But tech experts warn against conflating ethics as just another compliance checklist. Jane Pinelis, who leads test, evaluation, and assessment for the DOD's Joint Artificial Intelligence Center, said preserving personal health information is one of the JAIC's biggest priorities. "On the health side, one of the biggest things that we're concerned about is the preservation of personal health information," Pinelis said during an Oct. 22 Defense One NextGov event on AI. "On something else, we might be worried about equitability and bias, how do we train these models, what kind of data do we use in training them, and what does that mean about future applications." The JAIC announced progress with its Predictive Health effort on Oct. 21, which aims to reduce the time it takes to diagnose cancer.

A Simple Tactic That Could Help Reduce Bias in AI


That's an emerging conclusion of research-based findings -- including my own -- that could lead to AI-enabled decision-making systems being less subject to bias and better able to promote equality. This is a critical possibility, given our growing reliance on AI-based systems to render evaluations and decisions in high-stakes human contexts, in everything from court decisions, to hiring, to access to credit, and more. It's been well-established that AI-driven systems are subject to the biases of their human creators -- we unwittingly "bake" biases into systems by training them on biased data or with "rules" created by experts with implicit biases. Consider the Allegheny Family Screening Tool (AFST), an AI-based system predicting the likelihood a child is in an abusive situation using data from the same-named Pennsylvania county's Department of Human Services -- including records from public agencies related to child welfare, drug and alcohol services, housing, and others. Caseworkers use reports of potential abuse from the community, along with whatever publicly-available data they can find for the family involved, to run the model, which predicts a risk score from 1 to 20; a sufficiently high score triggers an investigation.

Strong ratings for top 5 AI providers but specialists make their mark, says PAC - The EE


PAC has published its PAC INNOVATION RADAR "AI-related Services in Germany 2020". For this evaluation, PAC analysed the services related to artificial intelligence (AI) offered by nearly 30 providers. A total of 21 organisations made it into the final assessment. Detailed evaluations in a total of seven business process-related segments show that when selecting a suitable service partner, user companies are well advised to also consider second-tier providers and specialists. The overall evaluation of the PAC INNOVATION RADAR "AI-related Services in Germany 2020" is based on a catalogue of general criteria such as breadth of services, local delivery capability, and investments made in AI-specific solutions and methods as well as in the further training of employees.

Psychology: Motivation to learn declines with age due to reduction of activity in key brain circuit

Daily Mail - Science & tech

Motivation to learn new things and engage with life declines with age due to falling activity in a brain circuit that weighs costs and benefits, a study on mice suggested. US experts have been studying'striosomes' -- clusters of cells in the basal ganglia, a brain area linked to habit formation, movement control, emotion and addiction. They team found that striosomes are key to the decision making process when dealing with'approach-avoidance conflict' -- when a choice has both pros and cons. For example, one such thorny problem might be whether or not to take a new job that pays better, but would also call for a move away from family and friends. Working with mice, the researchers found that striosomal activity is correlated to the evaluation of costs and benefits -- but that this activity diminishes with age.

TensorFlow Sound Classification Tutorial


Tools to detect, decipher, and act on human speech are a dime a dozen, but when looking for a tool to identify sounds, like speech, animals, or music, we were hard-pressed to find something that worked. In this article, we'll walk you through how we built some sample sound classification projects using Tensorflow machine learning algorithms. In this article, we describe which tools were chosen, what challenges we faced, how we trained the model for TensorFlow, and how to run our open source project. We've also supplied the recognition results the DeviceHive, IoT platform, to use them in cloud services for 3rd party applications. Hopefully, you can learn from our experience and put our tool to good use.

A state-of-the-art open source chatbot


Facebook AI has built and open-sourced BlenderBot, the largest-ever open-domain chatbot. It outperforms others in terms of engagement and also feels more human, according to human evaluators. The culmination of years of research in conversational AI, this is the first chatbot to blend a diverse set of conversational skills -- including empathy, knowledge, and personality -- together in one system. We achieved this milestone through a new chatbot recipe that includes improved decoding techniques, novel blending of skills, and a model with 9.4 billion parameters, which is 3.6x more than the largest existing system. Today we're releasing the complete model, code, and evaluation set-up, so that other AI researchers will be able to reproduce this work and continue to advance conversational AI research.

Digital Healthcare in Latin America

Communications of the ACM

The healthcare system in Latin America (LATAM) has made significant improvements in the last few decades. Nevertheless, it still faces significant challenges, including poor access to healthcare services, insufficient resources, and inequalities in health that may lead to decreased life expectancy, lower quality of life, and poor economic growth. Digital Healthcare (DH) enables the convergence of innovative technology with recent advances in neuroscience, medicine, and public healthcare policy.a In this article, we discuss key DH efforts that can help address some of the challenges of the healthcare system in LATAM focusing on two countries: Brazil and Mexico. We chose to study DH in the context of Brazil and Mexico as both countries are good representatives of the situation of the healthcare system in LATAM and face similar challenges along with other LATAM countries. Brazil and Mexico have the largest economies in the region and account for approximately half of the population and geographic territory of LATAM.11

Best of for AI, Machine Learning, and Deep Learning – September 2020 - insideBIGDATA


Researchers from all over the world contribute to this repository as a prelude to the peer review process for publication in traditional journals. The articles listed below represent a small fraction of all articles appearing on the preprint server. They are listed in no particular order with a link to each paper along with a brief overview. Links to GitHub repos are provided when available. Especially relevant articles are marked with a "thumbs up" icon.