内容来源：OpenScience

如何在神经科学中使用人工神经网络

计算神经科学，即 Computational neuroscience，使用数学分析和计算机建模对行为、认知和神经系统多个层面进行模拟和研究。人工神经网络(Artificial neural networks)是深度学习领域的核心技术。伴随两个领域高速的发展，引发了一个处于学科交叉中的关键问题：人工神经网络如何作为有效的研究工具应用于解决计算神经科学中的重要问题？

本期我们邀请了来自于哥伦比亚大学理论神经科学中心(Center for Theoretical Neuroscience, Columbia University)的杨光宇博士(个人主页：http://guangyuyang.org/)，分享其最近发表的综述文章。

该文章对以上问题进行了系统而全面地梳理和介绍，而且附带了相关的python代码，可以作为入门此领域的绝佳教程。

在本次的报告中，杨同学将用2个小时，分别从理论和实操两个方面展开，对其综述文章和代码进行全面介绍。内容将十分精彩，非常值得期待！

时间：北京时间7月4日21:00 ~ 23:00

Zoom信息：https://auckland.zoom.us/j/97510541178?pwd=aThPQXlzRWtyR0hwd08wVDVWbHd5QT09

Meeting ID: 975 1054 1178

Password: 176471

报告人：杨光宇
Guangyu Robert Yang
(Center for Theoretical Neuroscience, Columbia University)

主持人：耿海洋
荷兰格罗宁根大学博士生
研究方向为跨精神疾病神经计算机制

题目：Artificial neural networks for neuroscientists: A primer

摘要

Artificial neural networks (ANNs) are essential tools in machine learning that are increasingly used for building computational models in neuroscience. Besides being powerful techniques for data analysis, ANNs provide a new approach for neuroscientists to build models that capture complex behaviors, neural activity and connectivity, as well as to explore optimization in neural systems. In this pedagogical Primer, we introduce conventional ANNs and demonstrate how they have been deployed to study neuroscience questions. Next, we detail how to customize the analysis, structure, and learning of ANNs to better address a wide range of challenges in brain research. To help the readers garner hands-on experience, this Primer is accompanied with tutorial-style code in PyTorch and Jupyter Notebook, covering major topics.

组织团队
NeuroChat
OpenScience