利用并调制混沌以从神经生成模型中采样
Harnessing and modulating chaos to sample from neural generative models
AI总结：
本研究展示了神经混沌在使大脑学习并从生成模型中采样方面的功能性作用，通过构建结合经典神经混沌模型与规范生成建模架构或基于能量的神经记忆模型的架构，实现了生物学上合理的采样率控制。
摘要：
混沌在强耦合的模型神经元循环网络中是普遍存在的，并被认为是大脑中容易达到的动力学状态。虽然神经混沌通常被视为稳健计算的障碍，但我们展示了这种混沌如何发挥功能性作用，使大脑能够学习并从生成模型中采样。我们构建了结合经典神经混沌模型与规范生成建模架构或基于能量的神经记忆模型的架构。我们展示了这些架构在采样方面具有吸引人的特性，包括通过整体增益调制轻松实现生物学上合理的采样率控制。
英文摘要：
Chaos is generic in strongly-coupled recurrent networks of model neurons, and thought to be an easily accessible dynamical regime in the brain. While neural chaos is typically seen as an impediment to robust computation, we show how such chaos might play a functional role in allowing the brain to learn and sample from generative models. We construct architectures that combine a classic model of neural chaos either with a canonical generative modeling architecture or with energy-based models of neural memory. We show that these architectures have appealing properties for sampling, including easy biologically-plausible control of sampling rates via overall gain modulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
