Part 2 –
Part 3 –

In the first of a four-part series, Yoshua Bengio opens his hour-long Keynote from October 2019 discussing the current state of Deep Learning and how Human-level AI capabilities have been worked toward in 2019.

Yoshua’s opening remarks proclaimed that there are principles giving rise to intelligence, both machine or animal, which can be described using the laws of physics. That is, that our intelligence is not gained through a big bag of tricks, but rather the use of mechanisms used to specifically acquire knowledge. Similar to the laws of physics, we should consider understanding the physical world, mostly by having figured out the laws of physics, not just by describing its consequences.

Join pioneers like Yoshua at RE•WORK events in 2020! See the full event listing here –

Can’t wait for the next section of Professor Bengio’s talk? You can see a high-level overview here –

Abstract: How could humans or machines discover high-level abstract representations which are not directly specified in the data they observe? The original goal of deep learning is to enable learning of such representations in a way that disentangles underlying explanatory factors. Ideally, this would mean that high-level semantic factors could be decoded from top-level representations with simple predictors like a linear classifier, trainable from very few examples. However, there are too many ways of representing the same information, and it is thus necessary to provide additional clues to the learner, which can be thought about as priors. We highlight several such priors. One of those priors is that high-level factors measured at different times (or places) have high mutual information, i.e., can be predicted from each other and contain many bits of information. We present recent work in unsupervised representation learning towards maximizing the mutual information between random variables. Finally, we introduce the novel idea that good representations should be robust under changes in distribution and show that this can, in fact, be used in a meta-learning setup to identify causal variables and how they are causally related.

Bio: Yoshua Bengio is recognized as one of the world’s leading experts in artificial intelligence (AI) and a pioneer in deep learning.

Since 1993, he has been a professor in the Department of Computer Science and Operational Research at the Université de Montréal. Holder of the Canada Research Chair in Statistical Learning Algorithms, he is also the founder and scientific director of Mila, the Quebec Institute of Artificial Intelligence, which is the world’s largest university-based research group in deep learning.

His research contributions have been undeniable. In 2018, Yoshua Bengio collected the largest number of new citations in the world for a computer scientist thanks to his many publications. The following year, he earned the prestigious Killam Prize in computer science from the Canada Council for the Arts and was co-winner of the A.M. Turing Prize, which he received jointly with Geoffrey Hinton and Yann LeCun, as well as the Excellence Awards of the Fonds de recherche du Québec – Nature et technologies.

Concerned about the social impact of AI, he actively contributed to the development of the Montreal Declaration for the Responsible Development of Artificial Intelligence.

Yoshua Bengio: “Deep Learning for AI”

This lecture will look back at some of the principles behind the recent successes of deep learning as well as acknowledge current limitations, and finally propose
research directions to build on top of this progress and towards human-level AI.
Notions of distributed representations, the curse of dimensionality, and compositionality with neural networks will be discussed, along with the fairly recent advances changing neural networks from pattern recognition devices to systems that can process any data structure thanks to attention mechanisms, and that can imagine novel but plausible configurations of random variables through deep generative networks. At the same time, analyzing the mistakes made by these systems suggests that the dream of learning a hierarchy of representations which disentangle the underlying high-level concepts (of the kind we communicate with language) is far from achieved. This suggests new research directions for deep learning, in particular from the agent perspective, with grounded language learning, discovering causal variables and causal structure, and the ability to explore in an unsupervised way to understand the world and quickly adapt to changes in it.

This video is also available on another stream:

The opinions expressed in this video do not necessarily reflect the views of the Heidelberg Laureate Forum Foundation or any other person or associated institution involved in the making and distribution of the video.

More information to the Heidelberg Laureate Forum:

More videos from the HLF:

AI pioneer Yoshua Bengio explores paths forward to human-level artificial intelligence at the January 2017 Asilomar conference organized by the Future of Life .

Yoshua Bengio, Yann LeCun, Demis Hassabis, Anca Dragan, Oren Etzioni, Guru Banavar, Jurgen Schmidhuber, and Tom Gruber discuss how and when we .

A revolution in AI is occurring thanks to progress in deep learning. How far are we towards the goal of achieving human-level AI? What are some of the main .

AI pioneer Yoshua Bengio explores paths forward to human-level artificial intelligence at the January 2017 Asilomar conference organized by the Future of Life .

In January 2017, AI pioneer Yoshua Bengio explores paths forward to human-level artificial intelligence and talks about breakthroughs in creating human level .

AI pioneer Yoshua Bengio explores paths forward to human-level artificial intelligence at the January 2017 Asilomar conference organized by the Future of Life .

When Microsoft acquired deep learning startup Maluuba in January, Maluuba’s highly respected advisor, the deep learning pioneer Yoshua Bengio, agreed to .

Elon Musk, Stuart Russell, Ray Kurzweil, Demis Hassabis, Sam Harris, Nick Bostrom, David Chalmers, Bart Selman, and Jaan Tallinn discuss with Max Tegmark .

During the mid-80s, Yoshua Bengio began his research in neural networks. This became the gateway to his career in artificial intelligence (AI) and deep learning (DL). In his presentation, Yoshua takes us through the evolution of DL: How it started in supervised learning, its progression from speech recognition to computer vision, till it reached human level processing and where we can expect it to go from here. At its core, of AI needs knowledge. Early models of AI failed as human knowledge, such as intuition, is implicit. DL was born as a way to let machines help intelligent decisions on its own. Empowered by increasing computational power and improved algorithms, DL and deep neural networks has advanced rapidly speech recognition, computer vision and natural language processing and visual question answering.

Yoshua Bengio (PhD in CS, McGill University, 1991), post-docs at M.I.T. (Michael Jordan) and AT&T Bell Labs (Yann LeCun), CS professor at Université de Montréal, Canada Research Chair in Statistical Learning Algorithms, NSERC Chair, CIFAR Fellow, member of NIPS foundation board and former program/general chair, co-created ICLR conference, authored two books and over 300 publications, the most cited being in the areas of deep learning, recurrent networks, probabilistic learning, natural language and manifold learning. He is among the most cited Canadian computer scientists and is or has been associate editor of the top journals in machine learning and neural networks.

This presentation took place at RE•WORK Deep Learning Summit in Boston, May 2016. View more videos from RE•WORK Summits here:

RE•WORK events bring together breakthrough technology, cutting-edge science and entrepreneurship to re-work the future, finding solutions to challenges in business and society.

More about our events:
More on this event:

AI pioneer Yoshua Bengio explores paths forward to human-level artificial intelligence at the January 2017 Asilomar conference organized by the Future of Life Institute.

The Beneficial AI 2017 Conference: In our sequel to the 2015 Puerto Rico AI conference, we brought together an amazing group of AI researchers from academia and industry, and thought leaders in economics, law, ethics, and philosophy for five days dedicated to beneficial AI. We hosted a two-day workshop for our grant recipients and followed that with a 2.5-day conference, in which people from various AI-related fields hashed out opportunities and challenges related to the future of AI and steps we can take to ensure that the technology is beneficial.

For more information on the BAI ‘17 Conference:

AI Principles

Beneficial AI 2017

A Principled AI Discussion in Asilomar

Presented at Activate 2018


There has been much progress in AI thanks to advances in deep learning in recent years, especially in areas such as computer vision, speech recognition, natural language processing, playing games, robotics, machine translation, etc. This presentation aims at introducing some of the core concepts and motivations behind deep learning and representation learning. Deep learning builds on many of the ideas introduced decades earlier with the connectionist approach to machine learning, inspired by the brain. These essential early contributions include the notion of distributed representation and the back-propagation algorithm for training multi-layer neural networks, but also the architecture of recurrent neural networks and convolutional neural networks. In addition to the substantial increase in computing power and dataset sizes, many modern additions have contributed to the recent successes. Thanks to soft-attention mechanisms neural nets have moved from pattern recognition devices working on vectors to general-purpose differentiable modular machines which can handle arbitrary data structures. The talk will end with a discussion of some major open problems for AI which are at the forefront of research in deep learning and reinforcement learning.

Learn more:

Yoshua Bengio, along with Geoffrey Hinton and Yann Lecun, is considered one of the three people most responsible for the advancement of deep learning during the 1990s, 2000s, and now. Cited 139,000 times, he has been integral to some of the biggest breakthroughs in AI over the past 3 decades.

This conversation is part of MIT 6.S099: Artificial General Intelligence. This class is free and open to everyone. Our goal is to take an engineering approach to exploring possible paths toward building human-level intelligence for a better world. Audio podcast version is available on

Course website:

– AI Podcast:
– Subscribe to this YouTube channel
– LinkedIn:
– Twitter:
– Facebook:
– Instagram:
– Slack:

A revolution in AI is occurring thanks to progress in deep learning. How far are we towards the goal of achieving human-level AI? What are some of the main challenges ahead?

Yoshua Bengio believes that understanding the basics of AI is within every citizen’s reach. That democratizing these issues is important so that our societies can make the best collective decisions regarding the major changes AI will bring, thus making these changes beneficial and advantageous for all.


Yoshua Bengio is one of the pioneers of Deep Learning. He is the head of the Montreal Institute for Learning Algorithms (MILA), Professor at the Université de Montréal, member of the NIPS board and co-founder of Element AI. With a PhD from McGill University (1991, Computer Science) and postdocs at MIT and AT&T Bell Labs, he holds the Canada Research Chair in Statistical Learning Algorithms, is a Senior Fellow of the Canadian Institute for Advanced Research and co-directs its program focused on deep learning. He is best known for his contributions to deep learning, recurrent nets, neural language models, neural machine translation and biologically inspired machine learning.


For more information visit

This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at

Yoshua Bengio talks about artificial intelligence through deep learning at TedXMontreal.

For the entire video The Rise of Artificial Intelligence through Deep Learning | Yoshua Bengio | TEDxMontreal click here: