A self-learning digital neural network using wafer-scale LSI

A large-scale, dual-network architecture using wafer-scale integration (WSI) technology is proposed. By using 0.8 mu m CMOS technology, up to 144 self-learning digital neurons were integrated on each of eight 5 in silicon wafers. Neural functions and the back-propagation (BP) algorithm were mapped to digital circuits. The complete hardware system packaged more than 1000 neurons within a 30 cm cube. The dual-network architecture allowed high-speed learning at more than 2 gigaconnections updated per second (GCUPS). The high fault tolerance of the neural network and proposed defect-handling techniques overcame the yield problem of WSI. This hardware can be connected to a host workstation and used to simulating a wide range of artificial neural networks. Signature verification and stock price prediction have already been demonstrated with this hardware. >

[1]  Bing J. Sheu,et al.  Digital VLSI multiprocessor design for neurocomputers , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2]  R. Ginosar,et al.  A digital systolic neural network chip (DSNC) , 1995, Eighteenth Convention of Electrical and Electronics Engineers in Israel.

[3]  Christian Lehmann,et al.  A generic systolic array building block for neural networks with on-chip learning , 1993, IEEE Trans. Neural Networks.

[4]  D. J. Myers,et al.  A high performance digital processor for implementing large artificial neural networks , 1991, Proceedings of the IEEE 1991 Custom Integrated Circuits Conference.

[5]  Y. Hirai,et al.  A digital neuro-chip with unlimited connectability for large scale neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[6]  A. Masaki,et al.  A wafer scale integration neural network utilizing completely digital circuits , 1989, International 1989 Joint Conference on Neural Networks.

[7]  M. Yagyu,et al.  Design, fabrication and evaluation of a 5-inch wafer scale neural network LSI composed on 576 digital neurons , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[8]  J. F. McDonald,et al.  The trials of wafer-scale integration: Although major technical problems have been overcome since WSI was first tried in the 1960s, commercial companies can't yet make it fly , 1984, IEEE Spectrum.

[9]  C.A. Neugebauer,et al.  Future trends in wafer scale integration , 1986, Proceedings of the IEEE.

[10]  D. Hammerstrom,et al.  A VLSI architecture for high-performance, low-cost, on-chip learning , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[11]  John Wawrzynek,et al.  The design of a neuro-microprocessor , 1993, IEEE Trans. Neural Networks.

[12]  Ran Ginosar,et al.  Neural-network-aided design for image processing , 1991, Other Conferences.

[13]  T. Watanabe,et al.  Neural network simulation on a massively parallel cellular array processor: AAP-2 , 1989, International 1989 Joint Conference on Neural Networks.

[14]  S. Y. Kung,et al.  Digital VLSI architectures for neural networks , 1989, IEEE International Symposium on Circuits and Systems,.

[15]  Takao Watanabe,et al.  A single 1.5-V digital chip for a 10/sup 6/-synapse neural network , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[16]  M. A. Bayoumi,et al.  A reconfigurable 'ANN' architecture , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.