Predicting protein cellular localization sites with a hardware analog neural network

Author

Hohmann, Steffen G. ; Schemmel, Johannes ; Schurmann, Felix ; Meier, Karlheinz

Author_Institution

Kirchhoff Inst. for Phys., Heidelberg Univ., Germany

Volume

1

fYear

2003

fDate

20-24 July 2003

Firstpage

381

Abstract

This paper presents experimental results obtained during the training of an analog hardware neural network for the prediction of cellular localization sites of proteins in yeast and E.coli. The synaptic weights of the network are optimized by an evolutionary chip-in-the-loop algorithm. The results provide a first demonstration of the applicability of the presented neural network architecture to real-world problems that require the ability to generalize and to handle quasi-continuous multi-bit inputs.

Keywords

analogue processing circuits; application specific integrated circuits; cellular biophysics; field programmable gate arrays; generalisation (artificial intelligence); genetic algorithms; learning (artificial intelligence); neural chips; neural net architecture; pattern classification; perceptrons; proteins; evolutionary chip-in-the-loop algorithm; hardware analog neural network; protein cellular localization sites; quasi-continuous multi-bit inputs; synaptic weights; Artificial neural networks; Cellular networks; Cellular neural networks; Fungi; Neural network hardware; Neural networks; Neurons; Parallel processing; Proteins; Scalability;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223376

Filename

1223376