AI Strategy and Concepts Bibliography

WIKINDX Resources

Beaulieu, S., Frati, L., Miconi, T., Lehman, J., Stanley, K. O., & Clune, J., et al. (2020). Learning to continually learn. arXiv preprint arXiv:2002.09571, 
Added by: SijanLibrarian (2021-11-08 13:18:15)   Last edited by: SijanLibrarian (2021-11-08 13:19:57)
Resource type: Journal Article
BibTeX citation key: Beaulieu2020
Email resource to friend
View all bibliographic details
Categories: Artificial Intelligence, Cognitive Science, Complexity Science, Computer Science, Data Sciences, Decision Theory, General, Neuroscience
Subcategories: Autonomous systems, Decision making, Deep learning, Machine intelligence, Machine learning, Neurosymbolic, Synthetic intelligence
Creators: Beaulieu, Cheney, Clune, Frati, Lehman, Miconi, Stanley
Collection: arXiv preprint arXiv:2002.09571
Views: 48/48
Views index: 24%
Popularity index: 6%
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to the problem. We instead advocate meta-learning a solution to catastrophic forgetting, allowing AI to learn to continually learn. Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML). It differentiates through a sequential learning process to meta-learn an activation-gating function that enables context-dependent selective activation within a deep neural network. Specifically, a neuromodulatory (NM) neural network gates the forward pass of another (otherwise normal) neural network called the prediction learning network (PLN). The NM network also thus indirectly controls selective plasticity (i.e. the backward pass of) the PLN. ANML enables continual learning without catastrophic forgetting at scale: it produces state-of-the-art continual learning performance, sequentially learning as many as 600 classes (over 9,000 SGD updates).
wikindx 6.2.2 ©2003-2020 | Total resources: 1447 | Username: -- | Bibliography: WIKINDX Master Bibliography | Style: American Psychological Association (APA) | Database queries: 65 | DB execution: 0.15622 secs | Script execution: 0.16976 secs