Use it or Lose it: Selective Memory and Forgetting in a Perpetual Learning Machine
Machine Learning
2015-09-30 v1
Abstract
In a recent article we described a new type of deep neural network - a Perpetual Learning Machine (PLM) - which is capable of learning 'on the fly' like a brain by existing in a state of Perpetual Stochastic Gradient Descent (PSGD). Here, by simulating the process of practice, we demonstrate both selective memory and selective forgetting when we introduce statistical recall biases during PSGD. Frequently recalled memories are remembered, whilst memories recalled rarely are forgotten. This results in a 'use it or lose it' stimulus driven memory process that is similar to human memory.
Cite
@article{arxiv.1509.03185,
title = {Use it or Lose it: Selective Memory and Forgetting in a Perpetual Learning Machine},
author = {Andrew J. R. Simpson},
journal= {arXiv preprint arXiv:1509.03185},
year = {2015}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1509.00913