# Adaptive structure evolution and biologically plausible synaptic plasticity for recurrent spiking neural networks

arXiv: https://arxiv.org/abs/2304.01015 · HTML: https://mlsanity.com/paper/2304.01015/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 53 references that are in the map.
- First posted on arXiv 31 Mar 2023.

## Builds on (most cited first, 7 of 7)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks](https://mlsanity.com/paper/1804.00227/) (2018)
- [Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity](https://mlsanity.com/paper/2111.01760/) (2021)
- [Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model](https://mlsanity.com/paper/1710.07354/) (2017)
- [A Neural Architecture Search based Framework for Liquid State Machine Design](https://mlsanity.com/paper/2004.07864/) (2020)
- [Learning spatiotemporal signals using a recurrent spiking network that discretizes time](https://mlsanity.com/paper/1907.08801/) (2019)
- [PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection](https://mlsanity.com/paper/2105.09909/) (2021)

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

- [Brain-inspired and Self-based Artificial Intelligence](https://mlsanity.com/paper/2402.18784/) (2024)

## Abstract (arXiv)

The architecture design and multi-scale learning principles of the human brain that evolved over hundreds of millions of years are crucial to realizing human-like intelligence. Spiking Neural Network (SNN) based Liquid State Machine (LSM) serves as a suitable architecture to study brain-inspired intelligence because of its brain-inspired structure and the potential for integrating multiple biological principles. Existing researches on LSM focus on different certain perspectives, including high-dimensional encoding or optimization of the liquid layer, network architecture search, and application to hardware devices. There is still a lack of in-depth inspiration from the learning and structural evolution mechanism of the brain. Considering these limitations, this paper presents a novel LSM learning model that integrates adaptive structural evolution and multi-scale biological learning rules. For structural evolution, an adaptive evolvable LSM model is developed to optimize the neural architecture design of liquid layer with separation property. For brain-inspired learning of LSM, we propose a dopamine-modulated Bienenstock-Cooper-Munros (DA-BCM) method that incorporates global long-term dopamine regulation and local trace-based BCM synaptic plasticity. Comparative experimental results on different decision-making tasks show that introducing structural evolution of the liquid layer, and the DA-BCM regulation of the liquid layer and the readout layer could improve the decision-making ability of LSM and flexibly adapt to rule reversal. This work is committed to exploring how evolution can help to design more appropriate network architectures and how multi-scale neuroplasticity principles coordinated to enable the optimization and learning of LSMs for relatively complex decision-making tasks.