I've found that the overwhelming majority of online information on artificial intelligence research falls into one of two categories: the first is aimed at explaining advances to lay audiences, and the second is aimed at explaining advances to other researchers. I haven't found a good resource for people with a technical background who are unfamiliar with the more advanced concepts and are looking for someone to fill them in. This is my attempt to bridge that gap, by providing approachable yet (relatively) detailed walkthroughs.
- Neural Episodic Control (2017 Mar)
- Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017 Feb)
- Overcoming Catastrophic Forgetting in Neural Networks (2017 Jan)
- Complementary Learning Systems Theory Updated (2016 July)
- One-shot Learning with Memory-Augmented Neural Networks (2016 May)
- Neural Turing Machine (2014 Oct)
- Asynchronous Methods for Deep Reinforcement Learning
- Approximate Hubel-Wiesel Modules and the Data Structures of Neural Computation
- Building Machines That Learn and Think Like People
- What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated
- In Overcoming Catastrophic Forgetting in Neural Networks, there were two additional neuroscience papers to read
- Fisher Information matrix
- Learning to Reinforcement Learn
- The successor representation in human reinforcement learning
- Human-level concept learning through probabilistic program induction
- MEMORY NETWORKS Jason Weston, Sumit Chopra & Antoine Bordes
- Algorithms for survival: a comparative perspective on emotions
- Hazy, T. E., Frank, M. J., and O’Reilly, R. C. (2006). Banishing the homunculus: making working memory work.
- Dayan, P. (2008). Simple substrates for complex cognition.
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence