analiza aiqbench
This research proposes a biologically inspired control framework that merges spike-based neural dynamics with Bayesian inference to handle adaptive tasks in uncertain environments. By benchmarking the model on nonlinear systems like the mountain car problem, the study demonstrates real-time state updates and goal-directed planning without relying on traditional differentiable architectures. The work serves as a significant bridge between computational neuroscience principles and probabilistic control theory, offering new pathways for robust AI agents.
Spike-based Belief Propagation in Nonlinear Dynamical Systems
arXiv:2608.19907v1 Announce Type: cross Abstract: This paper presents a Bayesian control framework that integrates spike-based dynamics with probabilistic inference for adaptive control. Bayesian inference is widely regarded as a core computational principle of brain function, providing a normative framework for perception, decision-making, and learning under uncertainty. By combining a biologically inspired spiking neural model with Bayesian inference principles, we propose a brain-like control algorithm capable of operating in uncertain environments. We use the mountain car parking problem as a benchmark with non-linear dynamics. Our results demonstrate that the proposed controller can successfully update states in real time and generate goal-directed action plans through spike-driven dynamics. The results highlight the proposed model's potential as a bridge between computational neuroscience and probabilistic control theory.
Abstract:This paper presents a Bayesian control framework that integrates spike-based dynamics with probabilistic inference for adaptive control. Bayesian inference is widely regarded as a core computational principle of brain function, providing a normative framework for perception, decision-making, and learning under uncertainty. By combining a biologically inspired spiking neural model with Bayesian inference principles, we propose a brain-like control algorithm capable of operating in uncertain environments. We use the mountain car parking problem as a benchmark with non-linear dynamics. Our results demonstrate that the proposed controller can successfully update states in real time and generate goal-directed action plans through spike-driven dynamics. The results highlight the proposed model's potential as a bridge between computational neuroscience and probabilistic control theory.
Accepted at NCTA 2026 (18th Int'l Conf. on Neural Computation Theory and Applications), part of IJCCI 2026, Angers, France. Pre-peer-review submitted version
Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Systems and Control (eess.SY)
arXiv:2608.19907 [cs.AI]
(or arXiv:2608.19907v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.19907 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 169 cuvinte
Subiecte conexe
Angles of attack for continual learning safety
LessWrong · 16 iun. 2026
Molybdenum disulfide transistors reshape spiking neural networks
Quantum Zeitgeist · 14 sept. 2026
Princeton University Defines Limits of Accurate Quantum Filtering
Quantum Zeitgeist · 10 sept. 2026
SALTO: Solver-Anchored Lifted Transfer Operators for Nonlinear Event Inference
arXiv · 16 oct. 2026