- ホーム
- > 洋書
- > ドイツ書
- > Mathematics, Sciences & Technology
- > Technology
- > electronics, electrical engineering, telecommunications
Full Description
This book discusses the acceleration of deep reinforcement learning (DRL), which may be the next step in the burst success of artificial intelligence (AI). The authors address acceleration systems which enable DRL on area-limited & battery-limited mobile devices. Methods are described that enable DRL optimization at the algorithm-, architecture-, and circuit-levels of abstraction.
Contents
Introduction.- Background of Deep Reinforcement Learning.- Group-Sparse Training Algorithm for Accelerating Deep Reinforcement Learning.- An Energy-Efficient Deep Reinforcement Learning Processor Design.- Low-power Autonomous Adaptation System with Deep Reinforcement Learning.- Low-power Autonomous Adaptation System with Deep Reinforcement Learning.- Exponent-Computing-in-Memory for DNN Training Processor with Energy-Efficient Heterogeneous Floating-point Computing Architecture.