# Continual learning under domain transfer with sparse synaptic bursting

arXiv: https://arxiv.org/abs/2108.12056 · HTML: https://mlsanity.com/paper/2108.12056/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 132 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 26 of 26)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Selective Experience Replay for Lifelong Learning](https://mlsanity.com/paper/1802.10269/) (2018)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Explicit Inductive Bias for Transfer Learning with Convolutional Networks](https://mlsanity.com/paper/1802.01483/) (2018)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Using Fast Weights to Attend to the Recent Past](https://mlsanity.com/paper/1610.06258/) (2016)
- [Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics](https://mlsanity.com/paper/2007.07400/) (2020)
- [Memory Efficient Experience Replay for Streaming Learning](https://mlsanity.com/paper/1809.05922/) (2018)
- [Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization](https://mlsanity.com/paper/1802.01569/) (2018)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win](https://mlsanity.com/paper/2010.03533/) (2020)
- [Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks](https://mlsanity.com/paper/1809.03142/) (2018)
- [Visual Explanations from Spiking Neural Networks using Interspike Intervals](https://mlsanity.com/paper/2103.14441/) (2021)
- [Neural networks grown and self-organized by noise](https://mlsanity.com/paper/1906.01039/) (2019)

## Built on by (most cited first, 1 of 1)

- [The Bayesian Approach to Continual Learning: An Overview](https://mlsanity.com/paper/2507.08922/) (2025)

## Abstract (arXiv)

Existing machines are functionally specific tools that were made for easy prediction and control. Tomorrow's machines may be closer to biological systems in their mutability, resilience, and autonomy. But first they must be capable of learning and retaining new information without being exposed to it arbitrarily often. Past efforts to engineer such systems have sought to build or regulate artificial neural networks using disjoint sets of weights that are uniquely sensitive to specific tasks or inputs. This has not yet enabled continual learning over long sequences of previously unseen data without corrupting existing knowledge: a problem known as catastrophic forgetting. In this paper, we introduce a system that can learn sequentially over previously unseen datasets (ImageNet, CIFAR-100) with little forgetting over time. This is done by controlling the activity of weights in a convolutional neural network on the basis of inputs using top-down regulation generated by a second feed-forward neural network. We find that our method learns continually under domain transfer with sparse bursts of activity in weights that are recycled across tasks, rather than by maintaining task-specific modules. Sparse synaptic bursting is found to balance activity and suppression such that new functions can be learned without corrupting extant knowledge, thus mirroring the balance of order and disorder in systems at the edge of chaos. This behavior emerges during a prior pre-training (or 'meta-learning') phase in which regulated synapses are selectively disinhibited, or grown, from an initial state of uniform suppression through prediction error minimization.