An inverse Hollis-Paulos artificial neural network

Author

Sellami, Louiza ; Newcomb, Robert W.

Author_Institution

Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA

Volume

9

Issue

5

fYear

1998

fDate

9/1/1998 12:00:00 AM

Firstpage

979

Lastpage

986

Abstract

The Hollis-Paulos artificial neural network (1990) [HPANN] is convenient in terms of its possibility for realization of variable weight artificial neural networks in VLSI by MOS transistor circuits, though it is nondynamical and not driven by external inputs. Here we introduce dynamics and inputs into the HPANN and show that over the range of operation covered by the Hollis-Paulos theory the system has an inverse. In particular, we derive that inverse, in semistate form, and give simulation results on its operation, showing how well the input to the original HPANN can be recovered from the output of the HPANN when fed into the inverse system. A comparison is made with the previous inverse of the Hopfield ANN. Possible applications of these inverse systems are to decoding of transmitted ANN signals and to inverse filtering for the extraction of input signals from processed signals

Keywords

MOS analogue integrated circuits; VLSI; analogue processing circuits; deconvolution; integrated circuit design; inverse problems; neural chips; HPANN; MOS transistor circuits; VLSI; analog multipliers; input signals extraction; inverse Hollis-Paulos artificial neural network; inverse filtering; semistate form; transmitted ANN signal decoding; variable weight artificial neural network realization; Artificial neural networks; Circuits; Deconvolution; Filtering; Finite impulse response filter; MOSFETs; Neural networks; Neurons; Signal processing; Very large scale integration;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.712175

Filename

712175