Title :
Random neural networks with state-dependent firing neurons
Author :
Jo, Sungho ; Yin, Jijun ; Mao, Zhi-Hong
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Massachusetts Inst. of Technol., Cambridge, MA, USA
fDate :
7/1/2005 12:00:00 AM
Abstract :
This letter studies the properties of the random neural networks (RNNs) with state-dependent firing neurons. It is assumed that the times between successive signal emissions of a neuron are dependent on the neuron potential. Under certain conditions, the networks keep the simple product form of stationary solutions and exhibit enhanced capacity of adjusting the probability distribution of the neuron states. It is demonstrated that desired associative memory states can be stored in the networks.
Keywords :
content-addressable storage; neural nets; probability; associative memory states; probability distribution; random neural network; signal emissions; state dependent firing neurons; stationary solutions; Associative memory; Biological information theory; Biological neural networks; Biological system modeling; Biology computing; Capacity planning; Neural networks; Neurons; Probability distribution; Recurrent neural networks; Associative memory; random neural networks (RNNs); spiking neurons; state-dependent firing rate; Action Potentials; Algorithms; Computer Simulation; Models, Statistical; Neural Networks (Computer);
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2005.849829
