arXiv (Cornell University)· 2016· Preprint
Progressive Neural Networks
- 1,140citations
- 2016year
Short summary
Progressive networks, a novel architecture, overcome catastrophic forgetting and leverage prior knowledge through lateral connections, outperforming pretraining/finetuning baselines on reinforcement learning tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- Progressive networks prevent catastrophic forgetting by adding new network columns for each task.
- Lateral connections enable transfer of knowledge from previous tasks to new ones.
- The architecture outperforms pretraining and finetuning baselines on reinforcement learning tasks (Atari, 3D maze games).
- Transfer of knowledge occurs at both low-level sensory and high-level control layers.
AI-generated from the title and abstract; the full text is not read.
Abstract
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The progressive networks approach represents a step forward in this direction: they are immune to forgetting and can leverage prior knowledge via lateral connections to previously learned features. We evaluate this architecture extensively on a wide variety of reinforcement learning tasks (Atari and 3D maze games), and show that it outperforms common baselines based on pretraining and finetuning. Using a novel sensitivity measure, we demonstrate that transfer occurs at both low-level sensory and high-level control layers of the learned policy.
The authors' abstract, as published at the source. arXiv (Cornell University), 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Statistical and Nonlinear Physics
Statistical and Nonlinear PhysicsPhysics and Astronomy