Dynamic neural manifolds for flexible closed-loop control on neuromorphic hardware

• URL: http://arxiv.org/abs/2607.07373v1
• Date: Wed, 08 Jul 2026 13:05:46 GMT
• Title: Dynamic neural manifolds for flexible closed-loop control on neuromorphic hardware
• Abstract summary: Spiking network models link aspects of sequential neural activity to features of manifold geometry.<n>We present an implementation on the SpiNNaker 2 chip for real-time, closed-loop control.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In biological circuits, sequential neural activity evolves along dynamic, low-dimensional manifolds to enable flexible behavior. Spiking network models link aspects of this sequential activity to features of manifold geometry through specific circuit mechanisms, making dynamic neural manifolds parameterizable, and thereby offering an explainable framework for neural computation. Extending this framework to neuromorphic engineering, we present an implementation on the SpiNNaker 2 chip for real-time, closed-loop control. By allowing sensory inputs to modulate heterogeneous inhibition, gain, and transient currents, our architecture drives rapid subspace rotations to switch between behaviors, as well as fine-grained trajectory control within them. We validate this via a robotic simulation where an agent uses sensory feedback to dynamically reconfigure its manifold geometry to navigate through a maze. Our results establish dynamic manifolds as a feasible approach for explainable neuromorphic architectures and a substrate for investigating biological neural dynamics.

Related papers

• A neural-astrocyte architecture implements a hybrid automaton for evidence accumulation [0.0]
  Astrocytes are non-neuronal glial cells that are receiving widespread attention due to their emerging role in neural computation.<n>We study mechanisms by which astrocytes may augment the ability of neural networks to infer context in reinforcement learning settings.
  arXiv  Detail & Related papers  (2026-09-14T18:49:14Z)
• Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling [55.07411490538404]
  Topological Neural Dynamics (TND) is a sequence modeling framework that shifts from layer-wise to neuron-wise dynamics.<n>TND represents a neural system as a directed neuron graph, an interaction operator, and a local dynamics function.<n>We evaluate TND as a case study on a behavior cloning task in single-player Pong.
  arXiv  Detail & Related papers  (2026-06-19T10:18:24Z)
• Pendulum Model of Spiking Neurons [0.0]
  We propose a biologically inspired model of spiking neurons based on the dynamics of a damped, driven pendulum.<n>We present an analysis of single-neuron dynamics and extend the model to multi-neuron layers governed by Spike-Timing Dependent Plasticity (STDP) learning rules.
  arXiv  Detail & Related papers  (2025-07-29T18:21:51Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Exploring Gain-Doped-Waveguide-Synapse for Neuromorphic Applications: A Pulsed Pump-Signal Approach [0.0]
  We introduce the concept of Gain on Waveguide Dynamics for synapses, demonstrating how non-linear pulse transformations of input probe signals occur under various pump-probe configurations.<n>By harnessing the complex interactions of asynchronous spiking pump techniques and ion densities in excited states, our method produces event-driven responses that mirror natural neuronal functions.
  arXiv  Detail & Related papers  (2025-07-08T12:29:48Z)
• Allostatic Control of Persistent States in Spiking Neural Networks for perception and computation [79.16635054977068]
  We introduce a novel model for updating perceptual beliefs about the environment by extending the concept of Allostasis to the control of internal representations.<n>In this paper, we focus on an application in numerical cognition, where a bump of activity in an attractor network is used as a spatial numerical representation.
  arXiv  Detail & Related papers  (2025-03-20T12:28:08Z)
• IP$^{2}$-RSNN: Bi-level Intrinsic Plasticity Enables Learning-to-learn in Recurrent Spiking Neural Networks [20.88195975299024]
  We develop a recurrent spiking neural network with bi-level intrinsic plasticity (IP$2$-RSNN)<n>Our results indicate that the proposed bi-level intrinsic plasticity plays a critical role in enabling L2L in RSNNs.
  arXiv  Detail & Related papers  (2025-01-24T14:45:03Z)
• Contrastive-Signal-Dependent Plasticity: Self-Supervised Learning in Spiking Neural Circuits [61.94533459151743]
  This work addresses the challenge of designing neurobiologically-motivated schemes for adjusting the synapses of spiking networks. Our experimental simulations demonstrate a consistent advantage over other biologically-plausible approaches when training recurrent spiking networks.
  arXiv  Detail & Related papers  (2023-03-30T02:40:28Z)
• A Predictive Coding Account for Chaotic Itinerancy [68.8204255655161]
  We show how a recurrent neural network implementing predictive coding can generate neural trajectories similar to chaotic itinerancy in the presence of input noise. We propose two scenarios generating random and past-independent attractor switching trajectories using our model.
  arXiv  Detail & Related papers  (2021-06-16T16:48:14Z)
• Continuous Learning and Adaptation with Membrane Potential and Activation Threshold Homeostasis [91.3755431537592]
  This paper presents the Membrane Potential and Activation Threshold Homeostasis (MPATH) neuron model. The model allows neurons to maintain a form of dynamic equilibrium by automatically regulating their activity when presented with input. Experiments demonstrate the model's ability to adapt to and continually learn from its input.
  arXiv  Detail & Related papers  (2021-04-22T04:01:32Z)
• Deep Reinforcement Learning for Neural Control [4.822598110892847]
  We present a novel methodology for control of neural circuits based on deep reinforcement learning. We map neural circuits and their connectome into a grid-world like setting and infers the actions needed to achieve aimed behavior. Our framework successfully infers neuropeptidic currents and synaptic architectures for control of chemotaxis.
  arXiv  Detail & Related papers  (2020-06-12T17:41:12Z)

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.