AN ALL-ANALOG EXPANDABLE NEURAL-NETWORK LSI WITH ON-CHIP BACKPROPAGATION LEARNING

被引:73
作者
MORIE, T [1 ]
AMEMIYA, Y [1 ]
机构
[1] HOKKAIDO UNIV,FAC ENGN,SAPPORO,HOKKAIDO 060,JAPAN
关键词
D O I
10.1109/4.309904
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper proposes an all-analog neural network LSI architecture and a new learning procedure called contrastive backpropagation learning. In analog neural LSI's with on-chip backpropagation learning, inevitable offset errors that arise in the learning circuits seriously degrade the learning performance. Using the learning procedure proposed here, offset errors are canceled to a large extent and the effect of offset errors on the learning performance is minimized. This paper also describes a prototype LSI with 9 neurons and 81 synapses based on the proposed architecture which is capable of continuous neuron-state and continuous-time operation because of its fully analog and fully parallel property. Therefore, an analog neural system made by combining LSI's with feedback connections is promising for implementing continuous-time models of recurrent networks with real-time learning.
引用
收藏
页码:1086 / 1093
页数:8
相关论文
共 16 条
[1]  
ALSPECTOR J, 1992, ADV NEUR IN, V4, P871
[2]   A 336-NEURON, 28K-SYNAPSE, SELF-LEARNING NEURAL NETWORK CHIP WITH BRANCH-NEURON-UNIT ARCHITECTURE [J].
ARIMA, Y ;
MASHIKO, K ;
OKADA, K ;
YAMADA, T ;
MAEDA, A ;
NOTANI, H ;
KONDOH, H ;
KAYANO, S .
IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1991, 26 (11) :1637-1644
[3]   Contrastive Learning and Neural Oscillations [J].
Baldi, Pierre ;
Pineda, Fernando .
NEURAL COMPUTATION, 1991, 3 (04) :526-545
[4]   A CMOS 4-QUADRANT ANALOG MULTIPLIER [J].
BULT, K ;
WALLINGA, H .
IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1986, 21 (03) :430-435
[5]   ADAPTIVE NEURAL OSCILLATOR USING CONTINUOUS-TIME BACK-PROPAGATION LEARNING [J].
DOYA, K ;
YOSHIZAWA, S .
NEURAL NETWORKS, 1989, 2 (05) :375-385
[6]   A FLOATING-GATE ANALOG MEMORY DEVICE FOR NEURAL NETWORKS [J].
FUJITA, O ;
AMEMIYA, Y .
IEEE TRANSACTIONS ON ELECTRON DEVICES, 1993, 40 (11) :2029-2055
[7]  
GRIFFIN M, 1991, ISSCC DIG TECH PAPER, P180
[8]   NEURAL NETWORKS AT WORK [J].
HAMMERSTROM, D .
IEEE SPECTRUM, 1993, 30 (06) :26-32
[9]  
McClelland J. L., 1986, PARALLEL DISTRIBUTED, V1
[10]  
MORIE T, 1992, IEICE T ELECTRON, VE75C, P303