FPGA implementation of a systems identification module based upon Hopfield networks

The aim of this contribution is to implement a hardware module that performs parametric identification of dynamical systems. The design is based upon the methodology of optimization with Hopfield neural networks, leading to an adapted version of these networks. An outstanding feature of this modified Hopfield network is the existence of weights that vary with time. Since weights can no longer be stored in read-only memories, these dynamic weights constitute a significant challenge for digital circuits, in addition to the usual issues of area occupation, fixed-point arithmetic and nonlinear functions computations. The implementation, which is accomplished on FPGA circuits, achieves modularity and flexibility, due to the usage of parametric VHDL to describe the network. In contrast to software simulations, the natural parallelism of neural networks is preserved, at a limited cost in terms of circuitry cost and processing time. The functional simulation and the synthesis show the viability of the design. In particular, the FPGA implementation exhibits a reasonably fast convergence, which is required to produce accurate parameter estimations. Current research is oriented towards integrating the estimator within an embedded adaptive controller for autonomous systems.

[1]  Gonzalo Joya,et al.  Hopfield neural networks for optimization: study of the different dynamics , 2002 .

[2]  Francisco Sandoval Hernández,et al.  FPGA Implementation of Hopfield Networks for Systems Identification , 2005, IWANN.

[3]  Nouma Izeboudjen,et al.  Digital Implementation of Artificial Neural Networks: From VHDL Description to EPGA Implementation , 1999, IWANN.

[4]  S. Abe.  Theories on the Hopfield neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[5]  Geert Deconinck,et al.  A Massively Parallel Architecture for Hopfield-type Neural Network Computers , 2002 .

[6]  Eduardo Sanchez,et al.  Using On-Line Arithmetic and Reconfiguration for Neuroprocessor Implementations , 1999, IWANN.

[7]  Mark W. Spong,et al.  Robot dynamics and control , 1989 .

[8]  Miguel A. Atencia Ruiz,et al.  Stochastic analysis of the Abe formulation of Hopfield networks , 2005, ESANN.

[9]  W. E. Blanz,et al.  GANGLION-a fast field-programmable gate array implementation of a connectionist classifier , 1992 .

[10]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[11]  Jihan Zhu,et al.  FPGA Implementations of Neural Networks - A Survey of a Decade of Progress , 2003, FPL.

[12]  Ulrich Rückert,et al.  Dynamically Reconfigurable Hardware - A New Perspective for Neural Network Implementations , 2002, FPL.

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

[14]  X. Mao,et al.  Stochastic Hopfield neural networks , 2003 .

[15]  Kate Smith-Miles,et al.  Neural Networks for Combinatorial Optimization: A Review of More Than a Decade of Research , 1999, INFORMS J. Comput..

[16]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Zainalabedin Navabi,et al.  VHDL: Analysis and Modeling of Digital Systems , 1992 .

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

[19]  Gonzalo Joya,et al.  Parametric identification of robotic systems with stable time-varying Hopfield networks , 2004 .

[20]  Francisco Sandoval Hernández,et al.  Hopfield Neural Networks for Parametric Identification of Dynamical Systems , 2004, Neural Processing Letters.

[21]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[22]  José Manuel Ferrández,et al.  New Emulated Discrete Model of CNN Architecture for FPGA and DSP Applications , 2003, IWANN.

[23]  Gonzalo Joya,et al.  Dynamical analysis of continuous higher-order hopfield networks for combinatorial optimization. , 2005, Neural computation.

[24]  S. Sastry,et al.  Adaptive Control: Stability, Convergence and Robustness , 1989 .