摘要 |
A method of training a biological neural network using a controller includes the steps of applying a cycle comprising stimulating a neural network using the controller by applying at least an input signal to the network (204), detecting an output response of the network by the controller (206), modifying the stimulation of the neural network for at least a period of time if the response matches a desired at least approximate response (208), and repeating the cycle of stimulation, detection, and modification at least one more time (212) until the neural network is trained to generate a desired output response for said input signal. |
申请人 |
WIDE HORIZON HOLDINGS INC.;MAROM, SHIMON;SHAHAF, GODED;ROUSSO, BENNY;BEN HAIM, SHLOMO |
发明人 |
MAROM, SHIMON;SHAHAF, GODED;ROUSSO, BENNY;BEN HAIM, SHLOMO |