NEMar 5, 2014

Artificial Neuron Modelling Based on Wave Shape

arXiv:1403.1073v18 citations
Originality Incremental advance
AI Analysis

This work addresses a potential bottleneck in neural network design for researchers in computational neuroscience and AI, but appears incremental as it builds on traditional feedforward networks with a shape-matching twist.

The paper tackles the problem of improving artificial neural network processing by introducing a neuron model that matches wave-like shapes between input and output, aiming to facilitate easier transformation into desired output values through reinforcement via resonance and synapse construction.

This paper describes a new model for an artificial neural network processing unit or neuron. It is slightly different to a traditional feedforward network by the fact that it favours a mechanism of trying to match the wave-like 'shape' of the input with the shape of the output against specific value error corrections. The expectation is then that a best fit shape can be transposed into the desired output values more easily. This allows for notions of reinforcement through resonance and also the construction of synapses.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes