Design and characterization of analog VLSI neural network modules

A systematic method for testing large arrays of analog, digital, or mixed-signal circuit components that constitute VLSI neural networks is described. This detailed testing procedure consists of a parametric test and a behavioral test. Characteristics of the input neuron, synapse, and output neuron circuits are used to distinguish between faulty and useful chips. Stochastic analysis of the parametric test results can be used to predict chip yield information. Several measurement results from two analog neural network processor designs that are fabricated in 2 mu m double-polysilicon CMOS technologies are presented to demonstrate the testing procedure. >

[1]  Mani Soma.  Guest Editor's Introduction: Mixing Analog and Digital Systems , 1992, IEEE Des. Test Comput..

[2]  J. Doernberg,et al.  Full-speed testing of A/D converters , 1984 .

[3]  Edward J. McCluskey.  Verification Testing - A Pseudoexhaustive Test Technique , 1984, IEEE Trans. Computers.

[4]  C. Tomovich,et al.  MOSIS - A gateway to silicon , 1988, IEEE Circuits and Devices Magazine.

[5]  Oscal T.-C. Chen,et al.  A VLSI neural processor for image data compression using self-organization networks , 1992, IEEE Trans. Neural Networks.

[6]  Bozena Kaminska,et al.  Analog circuit fault diagnosis based on sensitivity computation and functional testing , 1992, IEEE Design & Test of Computers.

[7]  Richard Nohelty.  Test System Architecture for Testing Advanced Mixed-Signal Devices , 1986, ITC.

[8]  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.

[9]  Edgar Sánchez-Sinencio,et al.  A modular CMOS design of a Hamming network , 1992, IEEE Trans. Neural Networks.

[10]  Andrzej J. Strojwas,et al.  VLSI Yield Prediction and Estimation: A Unified Framework , 1986, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[11]  Wojciech Maly,et al.  Physically realistic fault models for analog CMOS neural networks , 1991 .

[12]  S. Tam,et al.  An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapses , 1990, International 1989 Joint Conference on Neural Networks.

[13]  John Paul Shen,et al.  The Design of Easily Testable VLSI Array Multipliers , 1984, IEEE Transactions on Computers.

[14]  Wojciech Maly,et al.  Testing oriented analysis of CMOS ICs with opens , 1988, [1988] IEEE International Conference on Computer-Aided Design (ICCAD-89) Digest of Technical Papers.

[15]  Tetsuro Itakura,et al.  Neuro chips with on-chip backprop and/or Hebbian learning , 1992, 1992 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[16]  W. R. Buckland,et al.  Statistical Theory and Methodology in Science and Engineering. , 1960 .

[17]  Parag K. Lala,et al.  Fault diagnosis in analog circuits using element modulation , 1992, IEEE Design & Test of Computers.

[18]  Arthur D. Friedman,et al.  Easily Testable Iterative Systems , 1973, IEEE Transactions on Computers.

[19]  Linda S. Milor,et al.  Detection of catastrophic faults in analog integrated circuits , 1989, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[20]  Bing J. Sheu,et al.  Neural network communication receiver based on the nonlinear filtering , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[21]  D. Blackman,et al.  A general purpose analog neural computer , 1989, International 1989 Joint Conference on Neural Networks.

[22]  Bing J. Sheu,et al.  Modified Hopfield neural networks for retrieving the optimal solution , 1991, IEEE Trans. Neural Networks.

[23]  Lawrence D. Jackel,et al.  An analog neural network processor with programmable topology , 1991 .

[24]  R. L. Wadsack,et al.  Fault modeling and logic simulation of CMOS and MOS integrated circuits , 1978, The Bell System Technical Journal.

[25]  Bing J. Sheu,et al.  Hardware annealing in electronic neural networks , 1991 .

[26]  Jacob A. Abraham,et al.  Functional Testing of Microprocessors , 1984, IEEE Transactions on Computers.

[27]  M. E. Levitt,et al.  Physical design of testable VLSI: techniques and experiments , 1990 .

[28]  Patrick M. Shea,et al.  Operational experience with a neural network in the detection of explosives in checked airline luggage , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[29]  Duncan M. Walker.  Yield simulation for integrated circuits , 1987 .

[30]  Andreas G. Andreou,et al.  Current-mode subthreshold MOS circuits for analog VLSI neural systems , 1991, IEEE Trans. Neural Networks.

[31]  Mani Soma,et al.  Built-in test of CMOS state machines with realistic faults: a system perspective , 1990 .

[32]  J. J. Paulos,et al.  Artificial neural networks using MOS analog multipliers , 1990 .

[33]  D. M. H. Walker,et al.  VLASIC: A Catastrophic Fault Yield Simulator for Integrated Circuits , 1986, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[34]  Melvin A. Breuer,et al.  Digital systems testing and testable design , 1990 .

[35]  Takeshi Sakata,et al.  A single 1.5-V digital chip for a 106 synapse neural network , 1993, IEEE Trans. Neural Networks.

[36]  John Paul Shen,et al.  Inductive Fault Analysis of MOS Integrated Circuits , 1985, IEEE Design & Test of Computers.

[37]  Bing J. Sheu,et al.  Analog floating-gate synapses for general-purpose VLSI neural computation , 1991 .

[38]  Larry Apfelbaum.  Improving In-Circuit Diagnosis of Analog Networks with Expert Systems Techniques , 1986, ITC.

[39]  Y. Tamura,et al.  A BiCMOS analog neural network with dynamically updated weights , 1992, 1990 37th IEEE International Conference on Solid-State Circuits.

[40]  K. Asakawa,et al.  Mobile robot control by a structured hierarchical neural network , 1990, IEEE Control Systems Magazine.

[41]  Janak H. Patel,et al.  A Hierarchical Approach to Test Vector Generation , 1987, 24th ACM/IEEE Design Automation Conference.

[42]  Bing J. Sheu,et al.  VLSI design of compact and high-precision analog neural network processors , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[43]  S. Anderson,et al.  A reconfigurable multi-chip analog neural network: recognition and back-propagation training , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[44]  Carver A. Mead,et al.  Implementing neural architectures using analog VLSI circuits , 1989 .

[45]  H.P. Graf,et al.  A reconfigurable CMOS neural network , 1990, 1990 37th IEEE International Conference on Solid-State Circuits.

[46]  Alan F. Murray,et al.  Pulse-stream VLSI neural networks mixing analog and digital techniques , 1991, IEEE Trans. Neural Networks.

[47]  H. Shinohara,et al.  A refreshable analog VLSI neural network chip with 400 neurons and 40 K synapses , 1992 .

[48]  Kimmo Kaski,et al.  Pulse-density modulation technique in VLSI implementations of neural network algorithms , 1990 .

[49]  Mani Soma.  A design-for-test methodology for active analog filters , 1990, Proceedings. International Test Conference 1990.

[50]  Terrence J. Sejnowski,et al.  Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[51]  G. Lewicki.  FORESIGHT: a fast turn-around and low cost ASIC prototyping alternative , 1990, Third Annual IEEE Proceedings on ASIC Seminar and Exhibit.

[52]  Hans G. Kerkhoff,et al.  Testability analysis of analog systems , 1990, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

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

[54]  Osamu Saito,et al.  An 8 G connections-per-second 54 mW digital neural network chip low-power chain-reaction architecture , 1992, 1992 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[55]  Yannis Tsividis,et al.  A reconfigurable VLSI neural network , 1992 .

[56]  Tarun Khanna,et al.  Foundations of neural networks , 1990 .

[57]  J. Alspector,et al.  A Cascadable Neural Network Chip Set With On-chip Learning Using Noise And Gain Annealing , 1992, 1992 Proceedings of the IEEE Custom Integrated Circuits Conference.

[58]  Bing J. Sheu,et al.  An analog neural network processor for self-organizing mapping , 1992, 1992 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[59]  Jenq-Neng Hwang,et al.  Parallel algorithms/architectures for neural networks , 1989, J. VLSI Signal Process..