mlsanityData to 7 Oct 2026

Continual task learning in natural and artificial agents

arXiv 2210.04520 ↗First posted 10 Oct 2022q-bio.NC cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

How do humans and other animals learn new tasks? A wave of brain recording studies has investigated how neural representations change during task learning, with a focus on how tasks can be acquired and coded in ways that minimise mutual interference. We review recent work that has explored the geometry and dimensionality of neural task representations in neocortex, and computational models that have exploited these findings to understand how the brain may partition knowledge between tasks. We discuss how ideas from machine learning, including those that combine supervised and unsupervised learning, are helping neuroscientists understand how natural tasks are learned and coded in biological brains.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 19 of its 96 references that are in the map. First posted on arXiv 10 Oct 2022.

Builds on

19 of 96 references.

References · 19

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  3. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  4. 2015Prioritized Experience Replaycited by 1,070
  5. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
  6. 2018On Lazy Training in Differentiable Programmingcited by 671
  7. 2018Stronger generalization bounds for deep nets via a compression approachcited by 306
  8. 2020Kernel and Rich Regimes in Overparametrized Modelscited by 302
  9. 2018A mathematical theory of semantic development in deep neural networkscited by 182
  10. 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 178
  11. 2018Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilizationcited by 104
  12. 2018Generative replay with feedback connections as a general strategy for continual learningcited by 103
7 more
  1. 2019Scaling description of generalization with number of parameters in deep learningcited by 83
  2. 2021Continual Backprop: Stochastic Gradient Descent with Persistent Randomnesscited by 79
  3. 2022The Neural Race Reduction: Dynamics of Abstraction in Gated Networkscited by 37
  4. 2022Compositional generalization through abstract representations in human and artificial neural networkscited by 21
  5. 2015On Simplicity and Complexity in the Brave New World of Large-Scale Neurosciencecited by 15
  6. 2022Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signalscited by 12
  7. 2022A Neural Network Model of Continual Learning with Cognitive Controlcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 4; 2026: 1.

12 papers.

  1. 2023How connectivity structure shapes rich and lazy learning in neural circuitscited by 15
  2. 2022Statistical mechanics of continual learning: variational principle and mean-field potentialcited by 9
  3. 2024Uncovering cognitive taskonomy through transfer learning in masked autoencoder-based fMRI reconstructioncited by 7
  4. 2023A framework for the emergence and analysis of language in social learning agentscited by 2
  5. 2025Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamicscited by 2
  6. 2024Temporal-Difference Variational Continual Learningcited by 1
  7. 2025Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Examplecited by 1
  8. 2025Separating the what and how of compositional computation to enable reuse and continual learningcited by 1
  9. 2025Contribution of task-irrelevant stimuli to drift of neural representationscited by 1
  10. 2023Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causescited by 0
  11. 2024Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptroncited by 0
  12. 2026RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agentscited by 0