Towards Hardware Acceleration of Neuroevolution for Multimedia Processing Applications on Mobile Devices

详细信息    查看全文

• 作者：Daniel Larkin ; Andrew Kinane ; Noel O’Connor
• 刊名：Lecture Notes in Computer Science
• 出版年：2006
• 出版时间：2006
• 年：2006
• 卷：4234
• 期：1
• 页码：1178-1188
• 全文大小：347 KB
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

This paper addresses the problem of accelerating large artificial neural networks (ANN), whose topology and weights can evolve via the use of a genetic algorithm. The proposed digital hardware architecture is capable of processing any evolved network topology, whilst at the same time providing a good trade off between throughput, area and power consumption. The latter is vital for a longer battery life on mobile devices. The architecture uses multiple parallel arithmetic units in each processing element (PE). Memory partitioning and data caching are used to minimise the effects of PE pipeline stalling. A first order minimax polynomial approximation scheme, tuned via a genetic algorithm, is used for the activation function generator. Efficient arithmetic circuitry, which leverages modified Booth recoding, column compressors and carry save adders, is adopted throughout the design.