Collaborating Authors


Complete Machine Learning & Data Science Bootcamp 2021


This is a brand new Machine Learning and Data Science course just launched and updated this month with the latest trends and skills for 2021! Become a complete Data Scientist and Machine Learning engineer! Join a live online community of 400,000 engineers and a course taught by industry experts that have actually worked for large companies in places like Silicon Valley and Toronto. Graduates of Andrei's courses are now working at Google, Tesla, Amazon, Apple, IBM, JP Morgan, Facebook, other top tech companies. You will go from zero to mastery!

Geoffrey Hinton has a hunch about what's next for AI

MIT Technology Review

Back in November, the computer scientist and cognitive psychologist Geoffrey Hinton had a hunch. After a half-century's worth of attempts--some wildly successful--he'd arrived at another promising insight into how the brain works and how to replicate its circuitry in a computer. "It's my current best bet about how things fit together," Hinton says from his home office in Toronto, where he's been sequestered during the pandemic. If his bet pays off, it might spark the next generation of artificial neural networks--mathematical computing systems, loosely inspired by the brain's neurons and synapses, that are at the core of today's artificial intelligence. His "honest motivation," as he puts it, is curiosity. But the practical motivation--and, ideally, the consequence--is more reliable and more trustworthy AI.

Machine Learning Ops Engineer


TONZ is a Montreal based start-up with a fundamentally different approach to audio processing. Our technology uses deep neural net machine learning models to learn audio effect transformations. Our technology does not adjust conventional digital signal processing parameters, but instead applies the learned spectral transformation directly to blocks of audio samples. This new approach leads to several product development benefits in music, communications, and entertainment. In your role as TONZ MLOPs/DevOps developer at you will develop and maintain operations and infrastructure supporting the machine learning data pipeline.

Building a Recommender System Using Graph Neural Networks


This post covers a research project conducted with Decathlon Canada regarding recommendation using Graph Neural Networks. The Python code is available on GitHub, and this subject was also covered in a 40min presentation Q&A available on Youtube. Graph Neural Networks (GNNs) have been soaring in popularity in the past years. From numerous academic papers to concrete implementations, multiple researchers have pushed forward the understanding of GNNs. One of the popular tasks tackled with this new methodology is recommendation.

Top AI-powered Wearables To Look Out For In 2021


Researchers from the University of Waterloo in Canada are working on developing prosthetic legs equipped with computer vision and deep-learning AI. The technologies thus employed will help legs function similar to an able-bodied person and adjust their motion by observing the surroundings. This is a case of yet another AI-powered wearable innovation with the potential to bring cheers for many. According to a report, the AI wearable market is expected to grow at a CAGR of around 30% and expected to reach a valuation of more than $180 billion by 2025. Further, the Ministry of Electronics and IT (MeitY) is soon planning to extend the PLI scheme for smart wearables, IoT, and VR products.

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning Artificial Intelligence

Progress in deep reinforcement learning (RL) research is largely enabled by benchmark task environments. However, analyzing the nature of those environments is often overlooked. In particular, we still do not have agreeable ways to measure the difficulty or solvability of a task, given that each has fundamentally different actions, observations, dynamics, rewards, and can be tackled with diverse RL algorithms. In this work, we propose policy information capacity (PIC) -- the mutual information between policy parameters and episodic return -- and policy-optimal information capacity (POIC) -- between policy parameters and episodic optimality -- as two environment-agnostic, algorithm-agnostic quantitative metrics for task difficulty. Evaluating our metrics across toy environments as well as continuous control benchmark tasks from OpenAI Gym and DeepMind Control Suite, we empirically demonstrate that these information-theoretic metrics have higher correlations with normalized task solvability scores than a variety of alternatives. Lastly, we show that these metrics can also be used for fast and compute-efficient optimizations of key design parameters such as reward shaping, policy architectures, and MDP properties for better solvability by RL algorithms without ever running full RL experiments.

Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification Artificial Intelligence

Fine-grained classification aims at distinguishing between items with similar global perception and patterns, but that differ by minute details. Our primary challenges come from both small inter-class variations and large intra-class variations. In this article, we propose to combine several innovations to improve fine-grained classification within the use-case of wildlife, which is of practical interest for experts. We utilize geo-spatiotemporal data to enrich the picture information and further improve the performance. We also investigate state-of-the-art methods for handling the imbalanced data issue.

Artificial Intelligence in Digital Pathology, Upcoming Webinar Hosted by Xtalks


TORONTO, March 19, 2021 /PRNewswire-PRWeb/ -- Which artificial intelligence method will work best with your image data? Image analysis is an essential part of digital pathology, from research and discovery of targets and biomarkers to understanding the tumor microenvironment to development of novel therapeutics. Whether you need to perform simple tasks or complex analysis of multiplex markers, artificial intelligence can improve performance and facilitate your analysis tasks to unlock the information hidden in image data. During the last years, deep learning algorithms have revolutionized the quality of analysis and allowed accurate assessment of highly heterogeneous and previously challenging tissue structures. In order to best utilize the capabilities that AI methods offer, however, it is important to understand what the terms "artificial intelligence" (AI), "machine learning" (ML), and "deep learning" (DL) really refer to when it comes to image analysis.

In the lab: Robotic AI-powered exoskeletons to help disabled people move freely without implants


Canadian boffins are testing semi-autonomous exoskeletons that could help people with limited mobility walk again without the need for implanted sensors. Researchers at the University of Waterloo, Ontario, are hard at work trying to combine modern deep-learning systems with robotic prostheses. They hope to give disabled patients who have suffered spinal cord injuries or strokes, or are inflicted with conditions including multiple sclerosis, spinal, cerebral palsy, and osteoarthritis, the ability to get back on their feet and move freely. The project differs from other efforts for amputees that involve trying to control the movement of machines using electrodes implanted in nerves and muscles in the limbs and brain, explained Brock Laschowski, a PhD student at the university who is leading the ExoNet study. "Our control approach wouldn't necessarily require human thought. Similar to autonomous cars that drive themselves, we're designing autonomous exoskeletons that walk for themselves."

Artificial Neural Nets Finally Yield Clues to How Brains Learn


In 2007, some of the leading thinkers behind deep neural networks organized an unofficial "satellite" meeting at the margins of a prestigious annual conference on artificial intelligence. The conference had rejected their request for an official workshop; deep neural nets were still a few years away from taking over AI. The bootleg meeting's final speaker was Geoffrey Hinton of the University of Toronto, the cognitive psychologist and computer scientist responsible for some of the biggest breakthroughs in deep nets. He started with a quip: "So, about a year ago, I came home to dinner, and I said, 'I think I finally figured out how the brain works,' and my 15-year-old daughter said, 'Oh, Daddy, not again.'" Hinton continued, "So, here's how it works."