Yann Le Cun: Predicting under Uncertainty, the Next Frontier in AI
professor Yann LeCun discussed about “predicting under uncertainty: the next frontier in AI” during the lecture at the University of Edinburgh
Category: Research
Technical review of the newest machine intelligence research.
David Silver, Google DeepMind: Deep Reinforcement Learning
There are three ways to combine DL and RL, based on three different principles: value-based, policy-based, and model-based approaches with planning.
Andrej Karpathy CS294 Lecture Review: Visualizing and Understanding Deep Neural Networks
This review will go over some of the current methods that are used to visualize and understand deep neural networks.
Monte Carlo Localization: Efficient Position Estimation for Mobile Robots
Sample-based Monte Carlo Localization is notable for its accuracy, efficiency, and ease of use in global localization and position tracking.
A Song from Artificial Intelligence
A University of Toronto Ph.D. student named Hang Chu recently published his project, a song completely composed and vocalized by Artificial Intelligence.
Combining Collaborative Filtering with Personal Agents for Better Recommendations
The 2017 award will be given to the most influential paper from the Sixteenth National Conference on Artificial Intelligence, held in 1999 in Orlando,USA.
Label-Free Supervision of Neural Networks with Physics and Domain Knowledge
The recipient of this year’s Outstanding Paper Award utilizes prior domain knowledge to constrain output space to a specific learning structure rather than a simple mapping from input to output
iPOP: The First Study on Personalized Medicine by Personal Big Data
This study is the first to perform extensive personal iPOP of an individual through healthy and diseased states. This paper was published in Cell, 2012.
Richard Sutton: The Future of Artificial Intelligence Belongs to Search and Learning
The future of AI belongs to scalable methods, search and learning; as presented by Richard Sutton in seminars at University of Toronto
Geoffrey Hinton: Using Fast Weights to Store Temporary Memories
Machine learning Advances and Applications Seminar address how to use fast weights to effectively store temporary memories, at University of Toronto
Google Brain’s Lukasz Kaiser: How Deep Learning Quietly revolutionized NLP
Lukasz Kaiser, Senior Research Scientist at Google Brain, gives a presentation about the developments in Natural Language Processing techniques at 2017’s AI Frontier Conference.
Super Gamer: Deep Q-network
Human-level control through deep reinforcement learning The theory of reinforcement learning provides a normative account, deeply rooted in psychological andContinue Reading
Interview with Dr.Richard Sutton: we might have strong AI algorithms by 2030
Professor Richard Sutton is considered to be one of the founding fathers of modern computational reinforcement learning. He made several significant contributions to the field, including temporal difference learning, policy gradient methods, and the Dyna architecture.
A Practical Guide to Neural Machine Translation
This talk focuses on engineer techniques for large-scale NMT systems. It helps us to understand how GPU works andContinue Reading
Machine Learning and the Market for Intelligence conference held by Creative Destruction Lab in Toronto
Yoshua Bengio, Geoffrey Hinton, Richard Sutton and Ruslan Salakhutdinov Panel Summary at 2016 I was at the 2016 “Machine LearningContinue Reading
Interview with John Markoff : A prophet in the age of AI
Born in Oakland, California on October 29, 1949, John Markoff grew up in Palo Alto, California and graduated from WhitmanContinue Reading