Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks
This addresses a critical stability issue for lifelong learning systems in robotics and AI, though it appears incremental as it builds on existing plasticity methods.
The paper tackles the problem of long-term instability in artificial neural networks with synaptic plasticity, showing that such networks degrade beyond their training lifespan, leading to failure in tasks like cart-pole balancing and quadrupedal locomotion. It proposes using spiking neurons as a solution to stabilize these networks.
Synaptic plasticity poses itself as a powerful method of self-regulated unsupervised learning in neural networks. A recent resurgence of interest has developed in utilizing Artificial Neural Networks (ANNs) together with synaptic plasticity for intra-lifetime learning. Plasticity has been shown to improve the learning capabilities of these networks in generalizing to novel environmental circumstances. However, the long-term stability of these trained networks has yet to be examined. This work demonstrates that utilizing plasticity together with ANNs leads to instability beyond the pre-specified lifespan used during training. This instability can lead to the dramatic decline of reward seeking behavior, or quickly lead to reaching environment terminal states. This behavior is shown to hold consistent for several plasticity rules on two different environments across many training time-horizons: a cart-pole balancing problem and a quadrupedal locomotion problem. We present a solution to this instability through the use of spiking neurons.