The following lists papers I’ve read and reviewed or made notes for.

Artificial General Intelligence

#

Alex Graves

#

• Automated Curriculum Learning for Neural Networks (2017)
• Multi-Dimensional Recurrent Neural Networks (2007)
• Neural Turing Machines (2014)
• Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks (2009)

Andrew Barto

#

• Intrinsically Motivated Learning of Hierarchical Collections of Skills (2004)

Andrew Carlson

#

• Toward an Architecture for Never-Ending Language Learning (2010)

Ashish Vaswani

#

• Attention Is All You Need (2017)

Barret Zoph

#

• Neural Architecture Search with Reinforcement Learning (2016)

Bradly Stadie

#

• Third-Person Imitation Learning (2017)

Burr Settles

#

• A Trainable Spaced Repetition Model for Language Learning (2016)

Carlos Florensa

#

• Reverse Curriculum Generation for Reinforcement Learning (2017)

Cristian Bucila

#

• Model Compression (2006)

David Silver

#

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017)
• Mastering the Game of Go with Deep Neural Networks and Tree Search (2016)
• Mastering the game of Go without human knowledge (2017)
• The Predictron: End-To-End Learning and Planning (2017)

Dzmitry Bahdanau

#

• Neural Machine Translation by Jointly Learning to Align and Translate (2015)

Eric Laukien

#

• Feynman Machine: The Universal Dynamical Systems Computer (2016)

Geoffrey Hinton

#

• Distilling the Knowledge in a Neural Network (2015)

Greg Linden

#

• Amazon.com Recommendations - Item-to-Item Collaborative Filtering (2003)

Ian Goodfellow

#

• Generative Adversarial Nets (2014)

J. R. Quinlan

#

• Induction of Decision Trees (1986)

Jacob Devlin

#

• RobustFill: Neural Program Learning under Noisy I/O (2017)

Karl Friston

#

• The free-energy principle: a unified brain theory? (2010)

Kelvin Xu

#

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (2015)

Ken Kansky

#

• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics (2017)

Leo Breiman

#

• Bagging Predictors (1996)

Levente Kocsis

#

• Bandit based Monte-Carlo Planning (2006)

Łukasz Kaiser

#

• One Model To Learn Them All (2017)

Manuel Lopes

#

• The Strategic Student Approach for Life-Long Exploration and Learning (2012)

Matej Balog

#

• DeepCoder: Learning to Write Programs (2016)

Matteo Hessel

#

• Rainbow: Combining Improvements in Deep Reinforcement Learning (2017)

Max Jaderberg

#

• Reading Text in the Wild with Convolutional Neural Networks (2014)

Miltiadis Allamanis

#

• SmartPaste: Learning to Adapt Source Code (2017)

Misha Denil

#

• Programmable Agents (2017)

Nal Kalchbrenner

#

• Grid Long Short-Term Memory (2015)

Neil Rabinowitz

#

• Machine Theory of Mind (2018)

Oriol Vinyals

#

• Starcraft II: A New Challenge for Reinforcement Learning (2017)

Paul Christiano

#

• Deep Reinforcement Learning from Human Preferences (2017)

Ralf Herbrich

#

• Learning and Generalization: Theoretical Bounds (2001)

Ronen Brafman

#

• R-max – A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning (2002)

Sercan Arik

#

• Deep Voice: Real-time Neural Text-to-Speech (2017)
• Deep Voice 2: Multi-Speaker Neural Text-to-Speech (2017)

Théodore Bluche

#

• Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention (2016)

Thomas Anthony

#

• Thinking Fast and Slow with Deep Learning and Tree Search (2017)

Tom Mitchell

#

• Never-ending learning (2018)

Tomas Mikolov

#

• Efficient Estimation of Word Representations in Vector Space (2013)

Volodymyr Mnih

#

• Human-level control through deep reinforcement learning (2015)
• Playing Atari with Deep Reinforcement Learning (2013)

Wei Ping

#

• Deep Voice 3: 2000-Speaker Neural Text-to-Speech (2017)

Xuan-Bach Le

#

• History Driven Program Repair (2016)

Yingfei Xiong

#

• Precise Condition Synthesis for Program Repair (2017)

Yoav Freund

#

• A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting (1995)

Yoshua Bengio

#

• Curriculum Learning (2009)
• The Consciousness Prior (2017)

Yuxuan Wang

#

• Tacotron: Towards End-to-End Speech Synthesis (2017)