Boosting Reservoir Computing with Brain-inspired Adaptive Dynamics

• URL: http://arxiv.org/abs/2504.12480v1
• Date: Wed, 16 Apr 2025 20:36:08 GMT
• Title: Boosting Reservoir Computing with Brain-inspired Adaptive Dynamics
• Authors: Keshav Srinivasan, Dietmar Plenz, Michelle Girvan,
• Abstract summary: Reservoir computers (RCs) provide a computationally efficient alternative to deep learning.<n>We show that RCs characteristically perform best in balanced or slightly over-inhibited regimes.<n>We introduce a self-adapting mechanism that locally adjusts E/I balance to achieve target neuronal firing rates.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reservoir computers (RCs) provide a computationally efficient alternative to deep learning while also offering a framework for incorporating brain-inspired computational principles. By using an internal neural network with random, fixed connections$-$the 'reservoir'$-$and training only the output weights, RCs simplify the training process but remain sensitive to the choice of hyperparameters that govern activation functions and network architecture. Moreover, typical RC implementations overlook a critical aspect of neuronal dynamics: the balance between excitatory and inhibitory (E-I) signals, which is essential for robust brain function. We show that RCs characteristically perform best in balanced or slightly over-inhibited regimes, outperforming excitation-dominated ones. To reduce the need for precise hyperparameter tuning, we introduce a self-adapting mechanism that locally adjusts E/I balance to achieve target neuronal firing rates, improving performance by up to 130% in tasks like memory capacity and time series prediction compared with globally tuned RCs. Incorporating brain-inspired heterogeneity in target neuronal firing rates further reduces the need for fine-tuning hyperparameters and enables RCs to excel across linear and non-linear tasks. These results support a shift from static optimization to dynamic adaptation in reservoir design, demonstrating how brain-inspired mechanisms improve RC performance and robustness while deepening our understanding of neural computation.

Related papers

• Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks [57.17129753411926]
  Spiking neural networks (SNNs) are emerging as a promising alternative to traditional artificial neural networks (ANNs)<n>We propose SpikeSR, which achieves state-of-the-art performance across various remote sensing benchmarks such as AID, DOTA, and DIOR.
  arXiv  Detail & Related papers  (2025-03-06T09:06:06Z)
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning [17.865755866792643]
  Reservoir computing (RC) is a recurrent neural network in which neurons are randomly connected. The model's rich dynamics, linear separability, and memory capacity then enable a simple linear readout to generate responses. RC spans areas far beyond machine learning, since it has been shown that the complex dynamics can be realized in various physical hardware implementations.
  arXiv  Detail & Related papers  (2023-07-27T05:20:20Z)
• Neuromorphic Control using Input-Weighted Threshold Adaptation [13.237124392668573]
  It is still challenging to replicate even basic low-level controllers such as proportional-integral-derivative (PID) controllers. We propose a neuromorphic controller that incorporates proportional, integral, and derivative pathways during learning. We demonstrate the stability of our bio-inspired algorithm with flights in the presence of disturbances.
  arXiv  Detail & Related papers  (2023-04-18T07:21:24Z)
• Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems [79.07468367923619]
  We propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC) We design an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards. We show that our proposed ActPC agent performs well in the face of sparse (extrinsic) reward signals and is competitive with or outperforms several powerful backprop-based RL approaches.
  arXiv  Detail & Related papers  (2022-09-19T16:49:32Z)
• Near-optimal control of dynamical systems with neural ordinary differential equations [0.0]
  Recent advances in deep learning and neural network-based optimization have contributed to the development of methods that can help solve control problems involving high-dimensional dynamical systems. We first analyze how truncated and non-truncated backpropagation through time affect runtime performance and the ability of neural networks to learn optimal control functions.
  arXiv  Detail & Related papers  (2022-06-22T14:11:11Z)
• Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning [1.9580473532948401]
  We introduce a novel neural network architecture inspired by neuromodulation in biological nervous systems. We show that this approach has strong learning performance per task despite the very small number of learnable parameters.
  arXiv  Detail & Related papers  (2022-04-08T21:12:13Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Adaptive Rational Activations to Boost Deep Reinforcement Learning [68.10769262901003]
  We motivate why rationals are suitable for adaptable activation functions and why their inclusion into neural networks is crucial. We demonstrate that equipping popular algorithms with (recurrent-)rational activations leads to consistent improvements on Atari games.
  arXiv  Detail & Related papers  (2021-02-18T14:53:12Z)
• Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning [56.83172249278467]
  We introduce Evolutionary Graph Reinforcement Learning (EGRL), a method designed for large search spaces. We train and validate our approach directly on the Intel NNP-I chip for inference. We additionally achieve 28-78% speed-up compared to the native NNP-I compiler on all three workloads.
  arXiv  Detail & Related papers  (2020-07-14T18:50:12Z)
• Recurrent Neural Network Learning of Performance and Intrinsic Population Dynamics from Sparse Neural Data [77.92736596690297]
  We introduce a novel training strategy that allows learning not only the input-output behavior of an RNN but also its internal network dynamics. We test the proposed method by training an RNN to simultaneously reproduce internal dynamics and output signals of a physiologically-inspired neural model. Remarkably, we show that the reproduction of the internal dynamics is successful even when the training algorithm relies on the activities of a small subset of neurons.
  arXiv  Detail & Related papers  (2020-05-05T14:16:54Z)
• VOR Adaptation on a Humanoid iCub Robot Using a Spiking Cerebellar Model [0.0]
  We embed a spiking cerebellar model within an adaptive real-time (RT) control loop that is able to operate a real robotic body (iCub) We aim to elucidate the manner in which the combination of the cerebellar neural substrate and the distributed plasticity shapes the cerebellar neural activity to mediate motor adaptation.
  arXiv  Detail & Related papers  (2020-03-03T09:48:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.