Overcoming catastrophic forgetting in neural networks
Top Cited Papers
Open Access
- 14 March 2017
- journal article
- research article
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences of the United States of America
- Vol. 114 (13) , 3521-3526
Abstract
Significance: Deep neural networks are currently the most successful machine-learning technique for solving a variety of tasks, including language translation, image classification, and image generation. One weakness of such models is that, unlike humans, they are unable to learn multiple tasks sequentially. In this work we propose a practical solution to train such models sequentially by protecting the weights important for previous tasks. This approach, inspired by synaptic consolidation in neuroscience, enables state of the art results on multiple reinforcement learning problems experienced sequentially.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Synapses with short-term plasticity are optimal estimators of presynaptic membrane potentialsNature Neuroscience, 2010
- Stably maintained dendritic spines are associated with lifelong memoriesNature, 2009
- Tag-Trigger-Consolidation: A Model of Early and Late Long-Term-Potentiation and DepressionPLOS Computational Biology, 2008
- Cascade Models of Synaptically Stored MemoriesNeuron, 2005
- Using Noise to Compute Error Surfaces in Connectionist Networks: A Novel Means of Reducing Catastrophic ForgettingNeural Computation, 2002
- Multiple Model-Based Reinforcement LearningNeural Computation, 2002
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999
- Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory.Psychological Review, 1995
- Uniqueness of the weights for minimal feedforward nets with a given input-output mapNeural Networks, 1992
- Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions.Psychological Review, 1990