One-to-one Mapping between Stimulus and Neural State: Memory and Classification
KeywordsQuantitative Biology - Neurons and Cognition
Computer Science - Machine Learning
Statistics - Machine Learning
Full recordShow full item record
AbstractSynaptic strength can be seen as probability to propagate impulse, and function could exist from propagation activity to synaptic strength. If the function satisfies constraints such as continuity and monotonicity, neural network under external stimulus would always go to fixed point, and there could be one-one-one mapping between external stimulus and synaptic strength at fixed point. In other words, neural network "memorizes" external stimulus in its synapses. A biological classifier is proposed to utilize this mapping.
Comment: 6 pages, 9 figures