Interplay: Dispersed Activation in Neural Networks
arXiv:1210.6082v1
Originality Synthesis-oriented
AI Analysis
This addresses memory efficiency in neural networks, but appears incremental as it builds on existing Hebbian methods.
The paper tackles the problem of memory recall speed in neural networks by using multi-point stimulation in a Hebbian network, achieving faster recall rates than single-point stimulus.
This paper presents a multi-point stimulation of a Hebbian neural network with investigation of the interplay between the stimulus waves through the neurons of the network. Equilibrium of the resulting memory is achieved for recall of specific memory data at a rate faster than single point stimulus. The interplay of the intersecting stimuli appears to parallel the clarification process of recall in biological systems.