NEMar 12, 2014

Memory Capacity of Neural Networks using a Circulant Weight Matrix

arXiv:1403.3115v12 citations
Originality Synthesis-oriented
AI Analysis

This work addresses memory capacity in neural networks, potentially relevant for understanding brain-inspired learning, but appears incremental as it applies an existing circulant matrix method to a feedback network without new data.

The paper investigates the memory capacity of a generalized feedback neural network using a circulant weight matrix, motivated by the idea that regular brain structures enable prior learning capacity, but no concrete results or numbers are provided in the abstract.

This paper presents results on the memory capacity of a generalized feedback neural network using a circulant matrix. Children are capable of learning soon after birth which indicates that the neural networks of the brain have prior learnt capacity that is a consequence of the regular structures in the brain's organization. Motivated by this idea, we consider the capacity of circulant matrices as weight matrices in a feedback network.

Foundations

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

Your Notes