DocumentCode :
750026
Title :
Competition and cooperation in neuronal processing
Author :
Bar, Haim ; Miranker, Willard L. ; Ambash, Alexander
Author_Institution :
Dept. of Comput. Sci., Yale Univ., New Haven, CT, USA
Volume :
14
Issue :
4
fYear :
2003
fDate :
7/1/2003 12:00:00 AM
Firstpage :
860
Lastpage :
868
Abstract :
A new type of model neuron is introduced as a building block of an associative memory. The neuron, which has a number of receptor zones, processes both the amplitude and the frequency of input signals, associating a small number of features encoded by those signals. Using this two-parameter input in our model compared to the one-dimensional inputs of conventional model neurons (e.g., the McCulloch Pitts neuron) offers an increased memory capacity. In our model, there is a competition among inputs in each zone with a subsequent cooperation of the winners to specify the output. The associative memory consists of a network of such neurons. A state-space model is used to define the neurodynamics. We explore properties of the neuron and the network and demonstrate its favorable capacity and recall capabilities. Finally, the network is used in an application designed to find trademarks that sound alike.
Keywords :
associative processing; content-addressable storage; learning (artificial intelligence); neural nets; associative memory; competition; competitive cooperative neuron; cooperation; memory capacity; model neuron; neural network; neural networks; neurodynamics; neuronal processing; one-dimensional inputs; recall; receptor zones; state-space model; trademarks; two-parameter input; Associative memory; Biological neural networks; Computer science; Frequency; Neurodynamics; Neurons; Protocols; Signal processing; Trademarks; Two dimensional displays;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/TNN.2003.813822
Filename :
1215403
Link To Document :
بازگشت