Noninvertibility in neural networks

A method for assessing certain validity aspects of predictions made by neural networks used to approximate continuous (in time) dynamical systems is presented. This method searches for noninvertibility (nonuniqueness of the reverse time dynamics) of the fitted model, an indication of breakdown of proper dynamical behavior. It is useful for computing bounds on the valid range of network predictions.<<ETX>>

[1]  Dale E. Seborg,et al.  Nonlinear internal model control strategy for neural network models , 1992 .

[2]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[3]  Edward N. Lorenz,et al.  Computational chaos-a prelude to computational instability , 1989 .

[4]  C. Robinson.  Dynamical Systems: Stability, Symbolic Dynamics, and Chaos , 1994 .

[5]  Ioannis G. Kevrekidis,et al.  Continuous time modeling of nonlinear systems: a neural network-based approach , 1993, IEEE International Conference on Neural Networks.

[6]  Mark A. Kramer,et al.  Algorithm 658: ODESSA–an ordinary differential equation solver with explicit simultaneous sensitivity analysis , 1988, TOMS.

[7]  Phillippe Langonnet.  Process control with neural networks: an example , 1992, Defense, Security, and Sensing.

[8]  Christian Mira,et al.  Recurrences and Discrete Dynamic Systems , 1980 .

[9]  Rahmat Shoureshi,et al.  A Neural Network Approach for Identification of Continuous-Time Nonlinear Dynamic Systems , 1991, 1991 American Control Conference.

[10]  C. Mira,et al.  Chaotic Dynamics: From the One-Dimensional Endomorphism to the Two-Dimensional Diffeomorphism , 1987 .

[11]  Laura Gardini.  Some global bifurcations of two-dimensional endomorphisms by use of critical lines , 1992 .

[12]  Ioannis G. Kevrekidis,et al.  Nonlinear signal processing and system identification: applications to time series from electrochemical reactions , 1990 .

[13]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[14]  C Mira,et al.  Chaotic Dynamics: From the One-Dimensional Endomorphism to the Two-Dimensional Diffeomorphism , 1987 .

[15]  A. Lapedes,et al.  Global bifurcations in Rayleigh-Be´nard convection: experiments, empirical maps and numerical bifurcation analysis , 1993, comp-gas/9305004.

[16]  James P. Crutchfield,et al.  Geometry from a Time Series , 1980 .

[17]  Oluseyi Olurotimi,et al.  Recurrent neural network training with feedforward complexity , 1994, IEEE Trans. Neural Networks.

[18]  Garrison W. Cottrell,et al.  Phase-Space Learning for Recurrent Networks , 1993 .

[19]  Ioannis G. Kevrekidis,et al.  DISCRETE- vs. CONTINUOUS-TIME NONLINEAR SIGNAL PROCESSING OF Cu ELECTRODISSOLUTION DATA , 1992 .

[20]  N.V. Bhat,et al.  Modeling chemical process systems via neural computation , 1990, IEEE Control Systems Magazine.

[21]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[22]  Raymond A. Adomaitis,et al.  On the Dynamics and Global Stability Characteristics of Adaptive Systems , 1991 .

[23]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[24]  Raymond A. Adomaitis,et al.  Noninvertibility and the structure of basins of attraction in a model adaptive control system , 1991 .

[25]  Yaman Arkun,et al.  Study of the control-relevant properties of backpropagation neural network models of nonlinear dynamical systems , 1992 .

[26]  A. Lapedes,et al.  Nonlinear signal processing using neural networks: Prediction and system modelling , 1987 .

[27]  Rahmat A. Shoureshi,et al.  Neural networks for system identification , 1990 .

[28]  Rutherford Aris,et al.  Rate multiplicity and oscillations in single species surface reactions , 1984 .

[29]  E. J. Doedel,et al.  AUTO: a program for the automatic bifurcation analysis of autonomous systems , 1980 .

[30]  B. Ydstie.  Forecasting and control using adaptive connectionist networks , 1990 .

[31]  Hong-Te Su,et al.  Identification of Chemical Processes using Recurrent Networks , 1991, 1991 American Control Conference.

[32]  Rahmat Shoureshi,et al.  Neural networks for system identification , 1989, IEEE Control Systems Magazine.

[33]  I.G. Kevrekidis,et al.  Continuous-time nonlinear signal processing: a neural network based approach for gray box identification , 1994, Proceedings of IEEE Workshop on Neural Networks for Signal Processing.

[34]  A. Lapedes,et al.  Nonlinear Signal Processing Using Neural Networks , 1987 .

[35]  Katharina Krischer,et al.  Chaos and Interior Crisis in an Electrochemical Reaction , 1991 .