Continual Learning Through Synaptic Intelligence
This addresses the continual learning challenge for AI systems that need to adapt to evolving data, representing an incremental improvement over existing methods.
The paper tackles the problem of catastrophic forgetting in deep learning when data distributions change over time, by introducing intelligent synapses that accumulate task-relevant information to store new memories without forgetting old ones, showing dramatic reduction in forgetting while maintaining computational efficiency.
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing domains, possibly by leveraging complex molecular machinery to solve many tasks simultaneously. In this study, we introduce intelligent synapses that bring some of this biological complexity into artificial neural networks. Each synapse accumulates task relevant information over time, and exploits this information to rapidly store new memories without forgetting old ones. We evaluate our approach on continual learning of classification tasks, and show that it dramatically reduces forgetting while maintaining computational efficiency.