Title :
A new mixed-signal feed-forward neural network with on-chip learning
Author :
Mirhassani, Mitra ; Ahmadi, M. ; Miller, W.C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Windsor Univ., Ont., Canada
Abstract :
A new mixed-signal feed-forward neural network for pattern/shape recognition problems is proposed. The network has a mixed-signal structure, operations are performed in analog and weights are stored in digital. To increase the network robustness, on-chip training with Madaline Rule III is used. The proposed architecture uses time-multiplexing to increase the network density and resistive-type neurons for their self-scaling property. The results of an XOR network are presented to test the network.
Keywords :
feedforward neural nets; learning (artificial intelligence); mixed analogue-digital integrated circuits; neural chips; neural net architecture; pattern recognition; system-on-chip; Madaline Rule III; XOR network; digital storage; mixed signal feedforward neural network; mixed signal structure; neural network density; neural network robustness; onchip learning; onchip training; pattern recognition; resistive type neurons; self scaling property; shape recognition; time multiplexing; Analog circuits; Complexity theory; Computer networks; Feedforward neural networks; Feedforward systems; Integrated circuit interconnections; Network-on-a-chip; Neural networks; Neurons; Robustness;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1380864
