A deep learning framework for neuroscience
A deep learning framework for neuroscience
复制标题
DOI：
10.1038/s41593-019-0520-2
复制
发表时间：
2019-11-01
影响因子：
25
通讯作者：
Kording, Konrad P.
中科院分区：
文献类型：
--
作者：
Richards, Blake A.;Lillicrap, Timothy P.;Kording, Konrad P.
系统神经科学寻求解释大脑如何实现各种各样的感知、认知和运动任务。相反，人工智能试图根据它们必须解决的任务来设计计算系统。在人工神经网络中，由设计指定的三个组成部分是目标函数、学习规则和体系结构。随着利用大脑启发架构的深度学习的日益成功，这三个设计组件越来越成为我们如何建模，工程和优化复杂人工学习系统的核心。在这里，我们认为，更多地关注这些组成部分也将有利于系统神经科学。我们举例说明这种基于优化的框架如何推动神经科学的理论和实验进展。我们认为，系统神经科学的这种原则性观点将有助于产生更快的进展。
Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In artificial neural networks, the three components specified by design are the objective functions, the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.