# Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks

arXiv: https://arxiv.org/abs/2106.07490 · HTML: https://mlsanity.com/paper/2106.07490/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2021.

## Built on by (most cited first, 15 of 15)

- [Simplicial Hopfield networks](https://mlsanity.com/paper/2305.05179/) (2023)
- [Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons](https://mlsanity.com/paper/2302.01228/) (2023)
- [A Normative and Biologically Plausible Algorithm for Independent Component Analysis](https://mlsanity.com/paper/2111.08858/) (2021)
- [Dendritic Self-Organizing Maps for Continual Learning](https://mlsanity.com/paper/2110.13611/) (2021)
- [The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks](https://mlsanity.com/paper/2306.16922/) (2023)
- [Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm](https://mlsanity.com/paper/2408.05834/) (2024)
- [Associative memory inspires improvements for in-context learning using a novel attention residual stream architecture](https://mlsanity.com/paper/2412.15113/) (2024)
- [Two Tales of Single-Phase Contrastive Hebbian Learning](https://mlsanity.com/paper/2402.08573/) (2024)
- [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)
- [Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural Networks](https://mlsanity.com/paper/2501.18018/) (2025)
- [Parameter efficient dendritic-tree neurons outperform perceptrons](https://mlsanity.com/paper/2207.00708/) (2022)
- [The Role Of Biology In Deep Learning](https://mlsanity.com/paper/2209.04425/) (2022)
- [Dendritic Integration Based Quadratic Neural Networks Outperform Traditional Aritificial Ones](https://mlsanity.com/paper/2307.13609/) (2023)
- [Perforated Neural Networks for Keyword Spotting](https://mlsanity.com/paper/2605.15647/) (2026)

## Abstract (arXiv)

This article highlights specific features of biological neurons and their dendritic trees, whose adoption may help advance artificial neural networks used in various machine learning applications. Advancements could take the form of increased computational capabilities and/or reduced power consumption. Proposed features include dendritic anatomy, dendritic nonlinearities, and compartmentalized plasticity rules, all of which shape learning and information processing in biological networks. We discuss the computational benefits provided by these features in biological neurons and suggest ways to adopt them in artificial neurons in order to exploit the respective benefits in machine learning.