Attractor Neural Networks

TL;DR

This paper discusses models of attractor neural networks designed as associative memories, highlighting their theoretical foundations and experimental comparisons with mammalian brain data.

Contribution

It introduces neural network models functioning as associative memories with multiple attractors representing different objects, and compares theoretical predictions with biological experiments.

Findings

Attractor neural networks can serve as effective associative memories.

Theoretical models align with experimental data from mammalian brains.

Different network attractors correspond to distinct object representations.

Abstract

In this lecture I will present some models of neural networks that have been developed in the recent years. The aim is to construct neural networks which work as associative memories. Different attractors of the network will be identified as different internal representations of different objects. At the end of the lecture I will present a comparison among the theoretical results and some of the experiments done on real mammal brains.