Timezone: »

 
Talk
Continual Learning Through Synaptic Intelligence
Friedemann Zenke · Ben Poole · Surya Ganguli

Mon Aug 07 06:06 PM -- 06:24 PM (PDT) @ Darling Harbour Theatre

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.

Author Information

Friedemann Zenke (Stanford)
Ben Poole (Stanford University)
Surya Ganguli (Stanford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors