artent.net
Artificial Intelligence Blog · Games
http://artent.net/category/games
We're blogging machines! You are currently browsing the archive for the Games. Newly Published “Deep Learning” Book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. April 7, 2016. In Deep Belief Networks. The book “Deep Learning” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (associated with the Google Deep Mind Team) is available in HTML format. Http:/ www.deeplearningbook.org/. Link: In Two Moves, AlphaGo and Lee Sedol Redefined the Future. March 16, 2016. March 9, 2016. March 30, 2015.
artent.net
Artificial Intelligence Blog · General ML
http://artent.net/category/general-ml
We're blogging machines! You are currently browsing the archive for the General ML. University of Alberta Solves Poker. January 9, 2015. The Daily Mail reports. That the Computer Poker Research Group at the University of Alberta. Seems to have solved heads-up limit hold’em poker. You can play against their AI online. My thanks to Glen for emailing me the story! 179 classifiers competing on 121 data sets and the winner is …. December 29, 2014. The overall result was that the random forest classifiers were...
artent.net
Artificial Intelligence Blog · Reinforcement Learning
http://artent.net/category/reinforcement-learning
We're blogging machines! You are currently browsing the archive for the Reinforcement Learning. Link: In Two Moves, AlphaGo and Lee Sedol Redefined the Future. March 16, 2016. Wired has a nice article about the two most brilliant moves in the historic match between AlphaGo. Http:/ www.wired.com/2016/03/two-moves-alphago-lee-sedol-redefined-future/. A Short Informal Description of Partially Observable Markov Decision Processes. May 3, 2015. There is a reward. When the world is in state. January 9, 2015.
artent.net
Artificial Intelligence Blog · A review of “Playing Atari with Deep Reinforcement Learning”
http://artent.net/2014/12/10/a-review-of-playing-atari-with-deep-reinforcement-learning
We're blogging machines! Lsaquo; A Review of Knowledge Vault: A Web-Scale Approach to a Probabilistic Knowledge Fusion. A short review of “Teaching Deep Convolutional Neural Networks to Play Go” ›. A review of Playing Atari with Deep Reinforcement Learning. December 10, 2014. Mnih, Kavukcuoglu, Silver, Graves, Antonoglon, Wierstra, and Riedmiller authored the paper Playing Atari with Deep Reinforcement Learning. By Diuk, Cohen, and Littman 2008, HyperNEAT-GGP:A HyperNEAT-based Atari General Game Player.
artent.net
Artificial Intelligence Blog · Neural Nets
http://artent.net/category/neural-nets
We're blogging machines! You are currently browsing the archive for the Neural Nets. Newly Published “Deep Learning” Book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. April 7, 2016. In Deep Belief Networks. The book “Deep Learning” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (associated with the Google Deep Mind Team) is available in HTML format. Http:/ www.deeplearningbook.org/. Link: In Two Moves, AlphaGo and Lee Sedol Redefined the Future. March 16, 2016. March 9, 2016. Recently, C...
artent.net
Artificial Intelligence Blog · We're blogging machines!
http://artent.net/page/2
We're blogging machines! University of Alberta Solves Poker. January 9, 2015. The Daily Mail reports. That the Computer Poker Research Group at the University of Alberta. Seems to have solved heads-up limit hold’em poker. You can play against their AI online. My thanks to Glen for emailing me the story! List of Papers for Carnegie Mellon’s Deep Learning Course. January 8, 2015. In Deep Belief Networks. CMU’s Professor Bhiksha Raj has a nice list of papers. December 29, 2014. The overall result was that t...
danvk.org
My takeaways from NIPS 2015
http://www.danvk.org/2015/12/12/nips-2015.html
Hex Dec converter in JavaScript. NS-Tower in the Browser. My takeaways from NIPS 2015. I’ve just wrapped up my trip to NIPS 2015. In Montreal and thought I’d jot down a few things that struck me this year:. Saddle Points vs Local Minima. Are effective at optimizing the thousands of weights in a neural net: they won’t get stuck in a local optimum. And it gives an intuition for why momentum. Is helpful: it helps gradient descent escape from saddle points. Hardware for Deep Learning. Images, the TIMIT.
jveness.info
Publications
http://www.jveness.info/publications/default.html
Research Scientist, Google DeepMind. Human-level control through deep reinforcement learning. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness. Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis. The Arcade Learning Environment:. An Evaluation Platform for General Agents. A Monte-Carlo AIXI Approximation.
jveness.info
About
http://www.jveness.info/about_me/default.html
Research Scientist, Google DeepMind. I am a 30-something Computer Scientist. At the moment I am working on various aspects of Monte-Carlo Tree Search, General Atari 2600 Game Playing. Universal source coding and reinforcement learning. I investigated some practical aspects of Marcus Hutter. S AIXI agent, a Bayesian optimality notion for reinforcement learning. My thesis is now available. My CV is available on request. I grew up in Penrith, later moving to Sydney to study at UNSW.
SOCIAL ENGAGEMENT