Randomized Algorithms: A System-Level, Poly-Time Analysis of Robust Computation

Provides a methodology for analyzing the performance degradation of a computation once it has been affected by perturbations. The suggested methodology, by relaxing all assumptions made in the related literature, provides design guidelines for the subsequent implementation of complex computations in physical devices. Implementation issues, such as finite precision representation, fluctuations of the production parameters and aging effects, can be studied directly at the system level, independent of any technological aspect and quantization technique. Only the behavioral description of the computational flow, which is assumed to be Lebesgue-measurable, and the architecture to be investigated are needed. The suggested analysis is based on the theory of randomized algorithms, which transforms the computationally intractable problem of robustness investigation into a polynomial-time algorithm by resorting to probability.

[1]  Danny Coomans,et al.  Classification Using Adaptive Wavelets for Feature Extraction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Vincenzo Piuri,et al.  Testability of artificial neural networks: A behavioral approach , 1995, J. Electron. Test..

[3]  M. Buckingham Noise in electronic devices and systems , 1983 .

[4]  Mathukumalli Vidyasagar,et al.  Learning and Generalization: With Applications to Neural Networks , 2002 .

[5]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[6]  Jenq-Neng Hwang,et al.  Finite precision error analysis of neural network electronic hardware implementations , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[7]  Youssef Saab,et al.  A Fast and Robust Network Bisection Algorithm , 1995, IEEE Trans. Computers.

[8]  Feng Zhou,et al.  High speed DCT/IDCT using a pipelined CORDIC algorithm , 1995, Proceedings of the 12th Symposium on Computer Arithmetic.

[9]  H. Chernoff A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations , 1952 .

[10]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[11]  Mathukumalli Vidyasagar,et al.  Statistical learning theory and randomized algorithms for control , 1998 .

[12]  Roberto Tempo,et al.  Probabilistic Robustness Analysis and Design of Uncertain Systems , 1999 .

[13]  Heinrich Meyr,et al.  The Differential CORDIC Algorithm: Constant Scale Factor Redundant Implementation without Correcting Iterations , 1996, IEEE Trans. Computers.

[14]  Cesare Alippi,et al.  Accuracy vs. Precision in Digital VLSI Architectures for Signal Processing , 1998, IEEE Trans. Computers.

[15]  Shantanu Dutt,et al.  Mantissa-Preserving Operations and Robust Algorithm-Based Fault Tolerance for Matrix Computations , 1996, IEEE Trans. Computers.

[16]  Minyue Fu,et al.  Worst-case properties of the uniform distribution and randomized algorithms for robustness analysis , 1998, Math. Control. Signals Syst..

[17]  Günhan Dündar,et al.  The effects of quantization on multilayer neural networks , 1995, IEEE Trans. Neural Networks.

[18]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[19]  Vincenzo Piuri,et al.  New trends in intelligent system design for embedded and measurement applications , 1999 .

[20]  Mathukumalli Vidyasagar,et al.  A Theory of Learning and Generalization: With Applications to Neural Networks and Control Systems , 1997 .

[21]  Bernard Widrow,et al.  Sensitivity of feedforward neural networks to weight errors , 1990, IEEE Trans. Neural Networks.

[22]  Philip Koopman,et al.  Embedded system design issues (the rest of the story) , 1996, Proceedings International Conference on Computer Design. VLSI in Computers and Processors.

[23]  Vincenzo Piuri,et al.  Sensitivity to errors in artificial neural networks: a behavioral approach , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[24]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[25]  Vincenzo Piuri,et al.  Sensitivity to errors in artificial neural networks: a behavioral approach , 1995 .

[26]  Stefan Friedrich,et al.  Topology , 2019, Arch. Formal Proofs.

[27]  Yu Hen Hu,et al.  A Novel Implementation of CORDIC Algorithm Using Backward Angle Recoding (BAR) , 1996, IEEE Trans. Computers.

[28]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[29]  Cesare Alippi A Perturbation Size-Independent Analysis of Robustness in Neural Networks by Randomized Algorithms , 2003 .

[30]  G. Troster,et al.  A high precision 1024-point FFT processor for 2D convolution , 1998, 1998 IEEE International Solid-State Circuits Conference. Digest of Technical Papers, ISSCC. First Edition (Cat. No.98CH36156).

[31]  Cesare Alippi,et al.  A Perturbation Size-independent Analysis of Robustness in Feedforward Neural Networks by Randomized Algorithms , 2001 .

[32]  Cesare Alippi Some guidelines to enhance application-level robustness in linear computation , 2000, Proceedings of the 43rd IEEE Midwest Symposium on Circuits and Systems (Cat.No.CH37144).

[33]  Jenq-Neng Hwang,et al.  Finite Precision Error Analysis of Neural Network Hardware Implementations , 1993, IEEE Trans. Computers.

[34]  AlippiCesare,et al.  Accuracy vs. Precision in Digital VLSI Architectures for Signal Processing , 1998 .

[35]  Cesare Alippi,et al.  FPE-based criteria to dimension feedforward neural topologies , 1999 .

[36]  H.J.A.F. Tulleken,et al.  Probabilistic robust controller design , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[37]  M. Vidyasagar An Overview of Computational Learning Theory and Its Applications to Neural Network Training , 1996 .

[38]  Sarunas Raudys,et al.  On Dimensionality, Sample Size, and Classification Error of Nonparametric Linear Classification Algorithms , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Steve W. Piche,et al.  The selection of weight accuracies for Madalines , 1995, IEEE Trans. Neural Networks.

[40]  Charles V. Stewart,et al.  Bias in robust estimation caused by discontinuities and multiple structures , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  Kemin Zhou,et al.  On the probabilistic characterization of model uncertainty and robustness , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[42]  Eduardo Sontag VC dimension of neural networks , 1998 .