Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren, +1

Image ClassificationDeep Neural NetworksMachine VisionImage AnalysisMachine Learning +12

ImageNet classification with deep convolutional neural networks

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

Communications of the ACM

Convolutional Neural NetworkEngineeringMachine LearningNeural NetworkImagenet Classification +17

Human-level control through deep reinforcement learning

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, +16

Nature

Artificial IntelligenceEngineeringDeep Reinforcement LearningReinforcement Learning (Educational Psychology)Computer Science +1

Reinforcement Learning: An Introduction

Richard S. Sutton, Andy Barto

IEEE Transactions on Neural Networks

Artificial IntelligenceEngineeringDeep Reinforcement LearningComputer ScienceRobot Learning +1

Reinforcement Learning: An Introduction

IEEE Transactions on Neural Networks

Artificial IntelligenceEngineeringDeep Reinforcement LearningStochastic GameGame Theory +7

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Sergey Ioffe

arXiv (Cornell University)

Data AugmentationDeep Neural NetworksMachine VisionMachine LearningData Science +13

Mastering the game of Go with deep neural networks and tree search

David Silver, Aja Huang, Chris J. Maddison, +17

Nature

Artificial IntelligenceGame AiDeep Neural NetworksEngineeringMachine Learning +8

In-Datacenter Performance Analysis of a Tensor Processing Unit

Norman P. Jouppi, Cliff Young, Nishant Patil, +72

Cluster ComputingEngineeringHardware AccelerationHigh-performance ArchitectureCloud Computing +12

Learning to Predict by the Methods of Temporal Differences

Richard S. Sutton

Machine Learning

EngineeringMachine LearningData ScienceTemporal DifferencesPredictive Analytics +6

Reinforcement learning in robotics: A survey

Jens Kober, J. Andrew Bagnell, Jan Peters

The International Journal of Robotics Research

Artificial IntelligenceEngineeringReinforcement Learning ApproachesRobotic AgentAutomation +9