# Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

arXiv: https://arxiv.org/abs/2203.11560 · HTML: https://mlsanity.com/paper/2203.11560/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 74 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Builds on (most cited first, 17 of 17)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Orthogonal Gradient Descent for Continual Learning](https://mlsanity.com/paper/1910.07104/) (2019)
- [Continual Learning of Context-dependent Processing in Neural Networks](https://mlsanity.com/paper/1810.01256/) (2018)
- [Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics](https://mlsanity.com/paper/2007.07400/) (2020)
- [Recurrent Neural Network for Text Classification with Multi-Task Learning](https://mlsanity.com/paper/1605.05101/) (2016)
- [Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization](https://mlsanity.com/paper/1802.01569/) (2018)
- [Continual Learning in Low-rank Orthogonal Subspaces](https://mlsanity.com/paper/2010.11635/) (2020)
- [Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway](https://mlsanity.com/paper/1411.6422/) (2014)
- [Continual Learning in the Teacher-Student Setup: Impact of Task Similarity](https://mlsanity.com/paper/2107.04384/) (2021)
- [Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future](https://mlsanity.com/paper/2001.07092/) (2020)
- [Continual Reinforcement Learning with Complex Synapses](https://mlsanity.com/paper/1802.07239/) (2018)
- [Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments](https://mlsanity.com/paper/2201.00042/) (2021)
- [A Neural Network Model of Continual Learning with Cognitive Control](https://mlsanity.com/paper/2202.04773/) (2022)

## Built on by (most cited first, 12 of 12)

- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Order parameters and phase transitions of continual learning in deep neural networks](https://mlsanity.com/paper/2407.10315/) (2024)
- [Continual task learning in natural and artificial agents](https://mlsanity.com/paper/2210.04520/) (2022)
- [Disentangling Representations through Multi-task Learning](https://mlsanity.com/paper/2407.11249/) (2024)
- [Curl Descent: Non-Gradient Learning Dynamics with Sign-Diverse Plasticity](https://mlsanity.com/paper/2510.02765/) (2025)
- [A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning](https://mlsanity.com/paper/2304.06738/) (2023)
- [Bridging Neuroscience and AI: Environmental Enrichment as a Model for Forward Knowledge Transfer](https://mlsanity.com/paper/2405.07295/) (2024)
- [The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation](https://mlsanity.com/paper/2502.03038/) (2025)
- [Separating the what and how of compositional computation to enable reuse and continual learning](https://mlsanity.com/paper/2510.20709/) (2025)
- [Optimal Learning Rate Schedule for Balancing Effort and Performance](https://mlsanity.com/paper/2601.07830/) (2026)
- [Context selectivity with dynamic availability enables lifelong continual learning](https://mlsanity.com/paper/2306.01690/) (2023)
- [Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causes](https://mlsanity.com/paper/2312.08519/) (2023)

## Abstract (arXiv)

Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational constraints for artificial neural networks, inspired by earlier work on gating in the primate prefrontal cortex, that capture the cost of interleaved training and allow the network to learn two tasks in sequence without forgetting. We augment standard stochastic gradient descent with two algorithmic motifs, so-called "sluggish" task units and a Hebbian training step that strengthens connections between task units and hidden units that encode task-relevant information. We found that the "sluggish" units introduce a switch-cost during training, which biases representations under interleaved training towards a joint representation that ignores the contextual cue, while the Hebbian step promotes the formation of a gating scheme from task units to the hidden layer that produces orthogonal representations which are perfectly guarded against interference. Validating the model on previously published human behavioural data revealed that it matches performance of participants who had been trained on blocked or interleaved curricula, and that these performance differences were driven by misestimation of the true category boundary.