Continual learning

Also catastrophic forgetting, catatrophic interference, lifelong learning

June 5, 2024 — June 5, 2024

algebra
graphical models
how do science
machine learning
networks
probability
statistics
Figure 1

Placeholder for noting the existence of the field of continual learning, i.e. training algorithms not just once but updating in the field. As such, it is something like the predictive-loss-minimization-equivalent of predictive coding, I guess.

Notoriously tricky because of catastrophic forgetting.

How do humans avoid this problem? Possibly sleep (Golden et al. 2022).

1 Incoming

2 References

Aleixo, Colonna, Cristo, et al. 2023. “Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy.”
Beaulieu, Frati, Miconi, et al. 2020. “Learning to Continually Learn.”
Daheim, Möllenhoff, Ponti, et al. 2024. “Model Merging by Uncertainty-Based Gradient Matching.”
De Lange, Aljundi, Masana, et al. 2021. “A Continual Learning Survey: Defying Forgetting in Classification Tasks.” IEEE Transactions on Pattern Analysis and Machine Intelligence.
French. 1999. “Catastrophic Forgetting in Connectionist Networks.” Trends in Cognitive Sciences.
Gers, Schmidhuber, and Cummins. 2000. “Learning to Forget: Continual Prediction with LSTM.” Neural Computation.
Golden, Delanois, Sanda, et al. 2022. “Sleep Prevents Catastrophic Forgetting in Spiking Neural Networks by Forming a Joint Synaptic Weight Representation.” PLOS Computational Biology.
Jiang, Shu, Wang, et al. 2022. “Transferability in Deep Learning: A Survey.”
Kirkpatrick, Pascanu, Rabinowitz, et al. 2017. “Overcoming Catastrophic Forgetting in Neural Networks.” Proceedings of the National Academy of Sciences.
Moreno-Muñoz, Artés-Rodríguez, and Álvarez. 2019. “Continual Multi-Task Gaussian Processes.” arXiv:1911.00002 [Cs, Stat].
Nguyen, Low, and Jaillet. 2020. “Variational Bayesian Unlearning.” In Advances in Neural Information Processing Systems.
Papamarkou, Skoularidou, Palla, et al. 2024. “Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI.”
Schirmer, Zhang, and Nalisnick. 2024. “Test-Time Adaptation with State-Space Models.”
Williams, and Zipser. 1989. “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks.” Neural Computation.