Scalable Biologically Inspired Neural Networks with Spike Time Based Learning

Author

Long, Lyle N.

Author_Institution

Pennsylvania State Univ., University Park, PA

fYear

2008

fDate

6-8 Aug. 2008

Firstpage

29

Lastpage

34

Abstract

This paper describes the software and algorithmic issues involved in developing scalable large-scale biologically inspired spiking neural networks. These neural networks are useful in object recognition and signal processing tasks, but will also be useful in simulations to help understand the human brain. The software is written using object oriented programming and is very general and usable for processing a wide range of sensor data and for data fusion.

Keywords

biology computing; brain; learning (artificial intelligence); neural nets; object recognition; object-oriented programming; sensor fusion; biologically inspired neural networks; biologically inspired spiking neural networks; data fusion; human brain; object oriented programming; object recognition; sensor data; signal processing tasks; spike time based learning; Biological neural networks; Biological system modeling; Biomedical signal processing; Brain modeling; Large-scale systems; Neural networks; Object oriented modeling; Object recognition; Signal processing algorithms; Software algorithms; hebbian; neural network; parallel; spiking; stdp;

fLanguage

English

Publisher

ieee

Conference_Titel

Learning and Adaptive Behaviors for Robotic Systems, 2008. LAB-RS '08. ECSIS Symposium on

Conference_Location

Edinburgh

Print_ISBN

978-0-7695-3272-1

Type

conf

DOI

10.1109/LAB-RS.2008.24

Filename

4599423