# Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks

## TL;DR

This paper introduces Controlled Forgetting Networks (CFNs), a biologically inspired method for unsupervised lifelong learning in spiking neural networks that selectively adapts to new information while preserving prior knowledge.

## Contribution

The paper presents a novel targeted plasticity mechanism using dopaminergic modulation to prevent catastrophic forgetting in SNNs during online learning.

## Key findings

- Achieved 95.36% accuracy on MNIST in an unsupervised lifelong learning setting.
- Demonstrated effective local adaptation without degrading performance on previous tasks.
- Validated the approach as potentially the best unsupervised single-layer SNN performance on MNIST.

## 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 local representations in a Spiking Neural Network (SNN) to adapt to novel information while protecting essential information in the remainder of the SNN from catastrophic forgetting. In our Controlled Forgetting Networks (CFNs), novel information triggers stimulated firing and heterogeneously modulated plasticity, inspired by biological dopamine signals, to cause rapid and isolated adaptation in the synapses of neurons associated with outlier information. This targeting controls the forgetting process in a way that reduces the degradation of accuracy for older tasks while learning new tasks. Our experimental results on the MNIST dataset validate the capability of CFNs to learn successfully over time from an unknown, changing environment, achieving 95.36% accuracy, which we believe is the best unsupervised accuracy ever achieved by a fixed-size, single-layer SNN on a completely disjoint MNIST dataset.