Name
Abstract | ||
|---|---|---|
The authors discuss how an analog signal can be encoded using biophysically realistic neural networks. Such a network differs from a standard artificial neural network because of the fact that a biological cell generates spikes and information is encoded as activity of this spike generator and transmitted through a synapse between two cells. Thus, a biological neural network is a dynamic ensemble of cells that interact, perhaps to approximate a function, perform a recursive computation such as solving a differential equation, or retain a variable in its memory. The interaction between the cells is controlled by choosing a set of synaptic weights that have to be optimized in order that a portion of the network encode a suitable function. A new optimization algorithm for finding a set of optimal synaptic weights has been proposed and successfully implemented using a software program called GENESIS. The algorithm is illustrated by implementing a memory which is a simple network of cells encoding the identity function, together with a unity feedback |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1109/ACC.2001.945552 | American Control Conference, 2001. Proceedings of the 2001 |
Keywords | DocType | Volume |
biocomputing,bioelectric potentials,biomembrane transport,encoding,neural nets,neurophysiology,optimisation,genesis,analog signal encoding,biological cell,biological neural network,biological neuron computation,biophysically realistic neural networks,differential equation,dynamic ensemble,identity function,information encoding,memory,optimal synaptic weights,optimization algorithm,recursive computation,software program,spike generator,standard artificial neural network,synapse,synaptic weights,unity feedback,computer networks,differential equations,artificial neural networks,artificial neural network,neural network | Conference | 1 |
ISSN | ISBN | Citations |
0743-1619 | 0-7803-6495-3 | 1 |
PageRank | References | Authors |
0.41 | 3 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zoran Nenadic | 1 | 21 | 3.92 |
| Ghosh, B.K. | 2 | 8 | 3.23 |
| zoran nenadict | 3 | 1 | 0.41 |
| bijoy k ghoshi | 4 | 1 | 0.41 |