Use it or Lose it: Selective Memory and Forgetting in a Perpetual Learning Machine
(Submitted on 10 Sep 2015)
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.
Comments:arXiv admin note: substantial text overlap witharXiv:1509.00913. substantial text overlap witharXiv:1509.00913
Subjects:Learning (cs.LG)
MSCclasses:68Txx
Cite as:arXiv:1509.03185[cs.LG]
(orarXiv:1509.03185v1[cs.LG]for this version)
Submission history
From: Andrew Simpson [view email]
[v1]Thu, 10 Sep 2015 15:12:00 GMT (316kb)
Download: