Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network

06/22/2019
by   Tomoki Kurikawa, et al.
4

Memories in neural system are shaped through the interplay of neural and learning dynamics under external inputs. By introducing a simple local learning rule to a neural network, we found that the memory capacity is drastically increased by sequentially repeating the learning steps of input-output mappings. The origin of this enhancement is attributed to the generation of a Psuedo-inverse correlation in the connectivity. This is associated with the emergence of spontaneous activity that intermittently exhibits neural patterns corresponding to embedded memories. Stablization of memories is achieved by a distinct bifurcation from the spontaneous activity under the application of each input.

READ FULL TEXT

page 2

page 3

page 4

page 9

page 10

research
07/30/2013

Neural Network Capacity for Multilevel Inputs

This paper examines the memory capacity of generalized neural networks. ...
research
01/24/2018

PRNN: Recurrent Neural Network with Persistent Memory

Although Recurrent Neural Network (RNN) has been a powerful tool for mod...
research
07/02/2010

Delta Learning Rule for the Active Sites Model

This paper reports the results on methods of comparing the memory retrie...
research
12/12/2022

Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees – Technical Report

Recurrent neural networks are capable of learning the dynamics of an unk...
research
01/24/2022

Input correlations impede suppression of chaos and learning in balanced rate networks

Neural circuits exhibit complex activity patterns, both spontaneously an...
research
11/14/2012

Memory Capacity of a Random Neural Network

This paper considers the problem of information capacity of a random neu...
research
03/03/2020

A Metric for Evaluating Neural Input Representation in Supervised Learning Networks

Supervised learning has long been attributed to several feed-forward neu...

Please sign up or login with your details

Forgot password? Click here to reset