Human-like Forgetting Curves in Deep Neural Networks
This work bridges cognitive science and neural network design to improve continual learning algorithms, though it is incremental in applying known principles to neural networks.
The study examined whether deep neural networks exhibit human-like forgetting curves, finding that Multi-Layer Perceptrons show such curves and that scheduled reviews enhance knowledge retention and mitigate catastrophic forgetting.
This study bridges cognitive science and neural network design by examining whether artificial models exhibit human-like forgetting curves. Drawing upon Ebbinghaus' seminal work on memory decay and principles of spaced repetition, we propose a quantitative framework to measure information retention in neural networks. Our approach computes the recall probability by evaluating the similarity between a network's current hidden state and previously stored prototype representations. This retention metric facilitates the scheduling of review sessions, thereby mitigating catastrophic forgetting during deployment and enhancing training efficiency by prompting targeted reviews. Our experiments with Multi-Layer Perceptrons reveal human-like forgetting curves, with knowledge becoming increasingly robust through scheduled reviews. This alignment between neural network forgetting curves and established human memory models identifies neural networks as an architecture that naturally emulates human memory decay and can inform state-of-the-art continual learning algorithms.