aceOvercoming catastrophic forgetting in neural networks
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, enable…
Protecting weights important for previous tasks enables deep neural networks to be trained sequentially and achieve state-of-the-art results on multiple reinforcement learning problems experienced sequentially.
Deep neural networks are unable to learn multiple tasks sequentially, suffering catastrophic forgetting when trained on new tasks.
Evidence
- Peer-reviewedProceedings of the National Academy of Sciences2017-03-14
How should this claim be treated?
Truvace Impact Record TRV-2026-0210, v1: “Overcoming catastrophic forgetting in neural networks.” Truvace, 2026-07-13. /record/TRV-2026-0210 (accessed at citation time). sha256 dbf9c1b78d0a35e4…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-0210 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.