A high-speed analog neural processor
暂无分享,去创建一个
Targeted at high-energy physics research applications, our special-purpose analog neural processor can classify up to 70 dimensional vectors within 50 nanoseconds. The decision-making process of the implemented feedforward neural network enables this type of computation to tolerate weight discretization, synapse nonlinearity, noise, and other non-ideal effects. Although our prototype does not take advantage of advanced CMOS technology, and was fabricated using a 2.5-/spl mu/m CMOS process, it performs 6 billion multiplications per second, with only 2 W dissipation, and has as high as 1.5 Gbyte/s equivalent bandwidth.<<ETX>>
[1] Klaas Hoen,et al. 20 Million Patterns Per Second VLSI Neural Network Pattern Classifier , 1993 .
[2] Klaas Hoen,et al. 20 million patterns per second analog CMOS neural network pattern classifier , 1993 .
[3] Bram Nauta. Analog CMOS Filters for Very High Frequencies , 1992 .
[4] Simon M. Tam,et al. Implementation and performance of an analog nonvolatile neural network , 1993 .
[5] Donald B. Alpert,et al. Architecture of the Pentium microprocessor , 1993, IEEE Micro.