# Learning to Act through Evolution of Neural Diversity in Random Neural Networks

arXiv: https://arxiv.org/abs/2305.15945 · HTML: https://mlsanity.com/paper/2305.15945/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 69 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 25 of 25)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Proving the Lottery Ticket Hypothesis: Pruning is All You Need](https://mlsanity.com/paper/2002.00585/) (2020)
- [Activation Functions: Comparison of trends in Practice and Research for Deep Learning](https://mlsanity.com/paper/1811.03378/) (2018)
- [Weight Agnostic Neural Networks](https://mlsanity.com/paper/1906.04358/) (2019)
- [Meta-Learning through Hebbian Plasticity in Random Networks](https://mlsanity.com/paper/2007.02686/) (2020)
- [Evolving Normalization-Activation Layers](https://mlsanity.com/paper/2004.02967/) (2020)
- [Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks](https://mlsanity.com/paper/1703.10371/) (2017)
- [Discovering Parametric Activation Functions](https://mlsanity.com/paper/2006.03179/) (2020)
- [Evolutionary Optimization of Deep Learning Activation Functions](https://mlsanity.com/paper/2002.07224/) (2020)
- [A Powerful Generative Model Using Random Weights for the Deep Image Representation](https://mlsanity.com/paper/1606.04801/) (2016)
- [The Quest for the Golden Activation Function](https://mlsanity.com/paper/1808.00783/) (2018)
- [Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules](https://mlsanity.com/paper/2104.07959/) (2021)
- [Evolving Parsimonious Networks by Mixing Activation Functions](https://mlsanity.com/paper/1703.07122/) (2017)
- [Meta-Reinforcement Learning with Self-Modifying Networks](https://mlsanity.com/paper/2202.02363/) (2022)
- [Learning to learn with backpropagation of Hebbian plasticity](https://mlsanity.com/paper/1609.02228/) (2016)

## Built on by (most cited first, 2 of 2)

- [Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents](https://mlsanity.com/paper/2404.15193/) (2024)
- [Evolving Reservoirs for Meta Reinforcement Learning](https://mlsanity.com/paper/2312.06695/) (2023)

## Abstract (arXiv)

Biological nervous systems consist of networks of diverse, sophisticated information processors in the form of neurons of different classes. In most artificial neural networks (ANNs), neural computation is abstracted to an activation function that is usually shared between all neurons within a layer or even the whole network; training of ANNs focuses on synaptic optimization. In this paper, we propose the optimization of neuro-centric parameters to attain a set of diverse neurons that can perform complex computations. Demonstrating the promise of the approach, we show that evolving neural parameters alone allows agents to solve various reinforcement learning tasks without optimizing any synaptic weights. While not aiming to be an accurate biological model, parameterizing neurons to a larger degree than the current common practice, allows us to ask questions about the computational abilities afforded by neural diversity in random neural networks. The presented results open up interesting future research directions, such as combining evolved neural diversity with activity-dependent plasticity.