Attention-Based Structural-Plasticity
This addresses the problem of lifelong learning for AI agents by mitigating catastrophic forgetting, though it appears incremental compared to existing methods.
The paper tackles catastrophic forgetting in neural networks by proposing an attention-based selective plasticity method inspired by the cholinergic neuromodulatory system, achieving competitive performance on benchmark tasks like Permuted MNIST and Split MNIST.
Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several efforts towards overcoming catastrophic forgetting in neural networks. Here, we propose a biologically inspired method toward overcoming catastrophic forgetting. Specifically, we define an attention-based selective plasticity of synapses based on the cholinergic neuromodulatory system in the brain. We define synaptic importance parameters in addition to synaptic weights and then use Hebbian learning in parallel with backpropagation algorithm to learn synaptic importances in an online and seamless manner. We test our proposed method on benchmark tasks including the Permuted MNIST and the Split MNIST problems and show competitive performance compared to the state-of-the-art methods.