# Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning

arXiv: https://arxiv.org/abs/2204.04297 · HTML: https://mlsanity.com/paper/2204.04297/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Linear Mode Connectivity in Multitask and Continual Learning](https://mlsanity.com/paper/2010.04495/) (2020)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [Continual Learning in Low-rank Orthogonal Subspaces](https://mlsanity.com/paper/2010.11635/) (2020)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Superposition of many models into one](https://mlsanity.com/paper/1902.05522/) (2019)
- [Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity](https://mlsanity.com/paper/2002.10585/) (2020)
- [Can a Fruit Fly Learn Word Embeddings?](https://mlsanity.com/paper/2101.06887/) (2021)
- [Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviours](https://mlsanity.com/paper/1812.09113/) (2018)
- [An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning](https://mlsanity.com/paper/2109.06663/) (2021)
- [Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection](https://mlsanity.com/paper/2111.10686/) (2021)

## Built on by (most cited first, 3 of 3)

- [Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics](https://mlsanity.com/paper/2501.06762/) (2025)
- [Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks](https://mlsanity.com/paper/2401.02437/) (2023)
- [Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental Learning](https://mlsanity.com/paper/2404.14588/) (2024)

## Abstract (arXiv)

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by metrics of catastrophic forgetting but also by computational efficiency and running time. Here, we introduce a novel neural network architecture inspired by neuromodulation in biological nervous systems to economically and efficiently address catastrophic forgetting and provide new avenues for interpreting learned representations. Neuromodulation is a biological mechanism that has received limited attention in machine learning; it dynamically controls and fine tunes synaptic dynamics in real time to track the demands of different behavioral contexts. Inspired by this, our proposed architecture learns a relatively small set of parameters per task context that neuromodulates the activity of unchanging, randomized weights that transform the input. We show that this approach has strong learning performance per task despite the very small number of learnable parameters. Furthermore, because context vectors are so compact, multiple networks can be stored concurrently with no interference and little spatial footprint, thus completely eliminating catastrophic forgetting and accelerating the training process.