具身神经计算框架：生物神经网络在网格世界导航任务中超越硅基 DQN
Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation
研究者提出具身神经计算（Embodied Neurocomputation）框架，用于优化硅计算接口与生物神经网络（BNN）之间的编码解码机制。团队在模拟网格世界中让 BNN 智能体沿气味梯度进行闭环导航，评估约 1,300 种参数组合、累计超过 4,000 小时实时交互，找到 12 种在多轮任务中稳定学习的配置，其任务表现显著高于同等交互预算下优化过的硅基 DQN 智能体。
Authors:Johnson Zhou, Daniel Tanneberg, Forough Habibollahi, Alon Loeffler, Kiaran Lawson, Valentina Baccetti, Kwaku Dad Abu-Bonsrah, Candice Desouza, Finn Doensen, Bradley Watmuff, Daria Kornienko, Azin Azadi, Justin Leigh Bourke, Bernhard Sendhoff, Brett J. Kagan
Abstract:Biological neural networks (BNNs) have been established as a powerful and adaptive substrate that offer the potential for incredibly energy and data efficient information processing with distinct learning mechanisms. Yet a core challenge to utilizing BNN for neurocomputation is determining the optimal encoding and decoding mechanisms between the traditional silicon computing interface and the living biology. Here, we propose an Embodied Neurocomputation framework as a systems-level approach to this multi-variable optimization encoding/decoding problem. We operationalize this approach through the first large-scale parameter optimization of encoding configurations for a BNN agent performing closed-loop navigation along an odor-style gradient in a simulated grid-world. Despite the relative simplicity of the task, the biological interactions gave rise to a massive multi-combinatorial search space for optimal parameters. By considering how the components of the system are interconnected and parameterized, we evaluated approximately 1,300 parameter combinations, over 4,000 hours of real-time agent-environment interactions, to identify 12 configurations that consistently demonstrated learning across multiple episodes. These configurations achieved significantly higher task performances than optimized silicon-based DQN agents under the same interaction budget. These findings represent an initial step toward robust and scalable goal-oriented learning using BNNs. Our framework establishes a foundation for applying task-driven neurocomputing and supports the development of field-wide benchmarks. In the long term, this work supports the development of hybrid bio-silicon architectures capable of efficient, adaptive and real-time computation, including the potential for robotic control applications.
| Comments: | 40th Conference on Neural Information Processing Systems (NeurIPS 2026) |
| Subjects: | Emerging Technologies (cs.ET); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Systems and Control (eess.SY); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2605.13315 [cs.ET] |
| (or arXiv:2605.13315v2 [cs.ET] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13315 arXiv-issued DOI via DataCite |
Submission history
From: Daniel Tanneberg [view email]
[v1]
Wed, 13 May 2026 10:27:05 UTC (9,383 KB)
[v2]
Fri, 2 Oct 2026 09:36:51 UTC (9,403 KB)
来源：arXiv：cs.LG · arxiv.org