Redwood Neuroscience
Title: “A Sparse Distributed Model of Episodic and Semantic Spatiotemporal
Memory”
Rod
Rinkus
Previous at Enkidu Research,
Inc.
Abstract:
A neural network model is proposed that forms sparse
spatiotemporal memory traces of spatiotemporal events given single occurrences
of the events. The traces are distributed in that each individual cell and
synapse participates in numerous traces. This sharing of representational
substrate provides the basis for similarity-based generalization and thus
semantic memory.
Simulation
results are provided demonstrating that similar spatiotemporal patterns map to
similar traces. The model achieves this property by measuring, on each time slice, the degree of
match, G, between the actual current
input pattern and the expected input pattern given the preceding time slices (i.e., temporal context) and then
adding an amount of noise, inversely
proportional to G, to the process of choosing the internal representation for the current time slice.
Thus, if G is small, indicating novelty, we add much noise and the resulting
internal representation of the current input pattern has low overlap with any
preexisting representations of time slices. If G is large, indicating a
familiar event, we add very little noise. This lets previously learned
associations, i.e., patterns of
increased synaptic weights, predominate in the choice of internal representation, resulting in reactivation of
all or most of the preexisting
representation of the input pattern.