Stimulating STDP to Exploit Locality for Lifelong Learning without Catastrophic Forgetting

  • Authors:
    Jason Allred (Purdue), Kaushik Roy (Purdue)
    Publication ID:
    P094551
    Publication Type:
    Paper
    Received Date:
    31-Aug-2018
    Last Edit Date:
    8-Feb-2019
    Research:
    2777.001 (Purdue University West Lafayette)

Abstract

Stochastic gradient descent requires that training samples be drawn from a uniformly random distribution of the data. For a deployed system that must learn online from an uncontrolled and unknown environment, the ordering of input samples often fails to meet this criterion, making lifelong learning a difficult challenge. We exploit the locality of the unsupervised Spike Timing Dependent Plasticity (STDP) learning rule to target subsets of a segmented Spiking Neural Network (SNN) to adapt to novel information while protecting the information in the remainder of the SNN from catastrophic forgetting. In our system, novel information triggers stimulated firing, inspired by biological dopamine signals, to boost STDP in the synapses of neurons associated with outlier information. This targeting controls the forgetting process in a way that reduces accuracy degradation while learning new information. Our preliminary results on the MNIST dataset validate the capability of such a system to learn successfully over time from an unknown, changing environment, achieving up to 93.88% accuracy for a completely disjoint dataset.

4819 Emperor Blvd, Suite 300 Durham, NC 27703 Voice: (919) 941-9400 Fax: (919) 941-9450

Important Information for the SRC website. This site uses cookies to store information on your computer. By continuing to use our site, you consent to our cookies. If you are not happy with the use of these cookies, please review our Cookie Policy to learn how they can be disabled. By disabling cookies, some features of the site will not work.