# Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations

arXiv: https://arxiv.org/abs/2205.11713 · HTML: https://mlsanity.com/paper/2205.11713/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 66 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (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)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines](https://mlsanity.com/paper/1810.12488/) (2018)
- [Understanding the Role of Training Regimes in Continual Learning](https://mlsanity.com/paper/2006.06958/) (2020)
- [Using Fast Weights to Attend to the Recent Past](https://mlsanity.com/paper/1610.06258/) (2016)
- [Continual Unsupervised Representation Learning](https://mlsanity.com/paper/1910.14481/) (2019)
- [A Simple Way to Initialize Recurrent Networks of Rectified Linear Units](https://mlsanity.com/paper/1504.00941/) (2015)
- [Iterative Amortized Inference](https://mlsanity.com/paper/1807.09356/) (2018)
- [Efficient Continual Learning with Modular Networks and Task-Driven Priors](https://mlsanity.com/paper/2012.12631/) (2020)
- [Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies](https://mlsanity.com/paper/1808.06508/) (2018)
- [Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates](https://mlsanity.com/paper/2010.00373/) (2020)
- [Credit Assignment in Neural Networks through Deep Feedback Control](https://mlsanity.com/paper/2106.07887/) (2021)
- [Unsupervised Continual Learning Via Pseudo Labels](https://mlsanity.com/paper/2104.07164/) (2021)
- [Concept Learning with Energy-Based Models](https://mlsanity.com/paper/1811.02486/) (2018)
- [Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget](https://mlsanity.com/paper/1905.10837/) (2019)
- [Thalamocortical contribution to solving credit assignment in neural systems](https://mlsanity.com/paper/2104.01474/) (2021)

## Built on by (most cited first, 4 of 4)

- [Gradient-based inference of abstract task representations for generalization in neural networks](https://mlsanity.com/paper/2407.17356/) (2024)
- [Flexible task abstractions emerge in linear networks with fast and bounded units](https://mlsanity.com/paper/2411.03840/) (2024)
- [Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causes](https://mlsanity.com/paper/2312.08519/) (2023)
- [Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing](https://mlsanity.com/paper/2502.15634/) (2025)

## Abstract (arXiv)

Animals thrive in a constantly changing environment and leverage the temporal structure to learn well-factorized causal representations. In contrast, traditional neural networks suffer from forgetting in changing environments and many methods have been proposed to limit forgetting with different trade-offs. Inspired by the brain thalamocortical circuit, we introduce a simple algorithm that uses optimization at inference time to generate internal representations of the current task dynamically. The algorithm alternates between updating the model weights and a latent task embedding, allowing the agent to parse the stream of temporal experience into discrete events and organize learning about them. On a continual learning benchmark, it achieves competitive end average accuracy by mitigating forgetting, but importantly, by requiring the model to adapt through latent updates, it organizes knowledge into flexible structures with a cognitive interface to control them. Tasks later in the sequence can be solved through knowledge transfer as they become reachable within the well-factorized latent space. The algorithm meets many of the desiderata of an ideal continually learning agent in open-ended environments, and its simplicity suggests fundamental computations in circuits with abundant feedback control loops such as the thalamocortical circuits in the brain.