Title :
A model of the neural network for storage and retrieval of temporal sequences
Author_Institution :
Inst. of Math. Problems of Biol., Acad. of Sci., Pushchino
Abstract :
A novel method for the storage and the retrieval of temporal sequences of frames (neural movies) using the backpropagation learning procedure is proposed. The strengths of the connections in the network are adjusted during learning to store the various sequences. The neural network is able to repeat periodically during retrieval one sequence of frames from the recorded set. A simulation model was used to study the properties and capabilities of the method
Keywords :
backpropagation; image sequences; information retrieval; information storage; neural nets; backpropagation learning; connection strengths; frames; neural movies; neural network; sequence repetition; simulation model; temporal sequence retrieval; temporal sequence storage; Biological system modeling; Biology computing; Motion pictures; Neural networks; Neurons; Sequences; Software algorithms;
Conference_Titel :
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location :
Rostov-on-Don
Print_ISBN :
0-7803-0809-3
DOI :
10.1109/RNNS.1992.268631
