# Neuromodulated Learning in Deep Neural Networks

arXiv: https://arxiv.org/abs/1812.03365 · HTML: https://mlsanity.com/paper/1812.03365/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2018.

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

- [Meta-Learning Bidirectional Update Rules](https://mlsanity.com/paper/2104.04657/) (2021)
- [Augmenting learning in neuro-embodied systems through neurobiological first principles](https://mlsanity.com/paper/2407.04525/) (2024)
- [Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics](https://mlsanity.com/paper/2501.06762/) (2025)

## Abstract (arXiv)

In the brain, learning signals change over time and synaptic location, and are applied based on the learning history at the synapse, in the complex process of neuromodulation. Learning in artificial neural networks, on the other hand, is shaped by hyper-parameters set before learning starts, which remain static throughout learning, and which are uniform for the entire network. In this work, we propose a method of deep artificial neuromodulation which applies the concepts of biological neuromodulation to stochastic gradient descent. Evolved neuromodulatory dynamics modify learning parameters at each layer in a deep neural network over the course of the network's training. We show that the same neuromodulatory dynamics can be applied to different models and can scale to new problems not encountered during evolution. Finally, we examine the evolved neuromodulation, showing that evolution found dynamic, location-specific learning strategies.