课程定位
CS 375(PSYCH 249)由 Dan Yamins 讲授,是计算神经科学与 AI 交叉的核心课。课程讨论人工网络的内部组件如何与真实大脑结构对应,覆盖前馈感知、循环动力学、注意力/记忆/导航、语言 Transformer、自监督和深度 RL,并教你如何把模型和神经数据做定量比较。
主要内容
- 前馈感知模型:视觉、听觉、体感
- 循环网络:动力学、运动控制
- 注意力/记忆/导航:整合模型
- 语言与 Transformer:语言区建模
- 自监督学习:与大脑学习机制对比
- 深度 RL:决策与规划
- 模型-神经数据比较:RSA、编码模型、指标
- 项目
课程大纲 / 课件
Winter 2026 calendar;slides 在 calendar 页逐次链接。
先修
现代神经网络背景(CS 229/230/231N/234/236/330 之一);不要求认知科学/神经科学背景。
考核与工作量
论文讨论 + 项目。具体以当季官网为准。
适合谁
NeuroAI、计算神经科学、AI 可解释性方向;想做“用 AI 理解大脑”的人。
学习建议
先修 CS 231N 或 CS 224N。配合 CS 322/EE 292R 拓宽视野。
相关课程
官方课程描述(英文原文)
The last ten years has seen a watershed in the development of large-scale neural networks in artificial intelligence. At the same time, computational neuroscientists have discovered a surprisingly robust mapping between the internal components of these networks and real neural structures in the human brain. In this class we will discuss a panoply of examples of such "convergent man-machine evolution", including: feedforward models of sensory systems (vision, audition, somatosensation); recurrent neural networks for dynamics and motor control; integrated models of attention, memory, and navigation; transformer models of language areas; self-supervised models of learning; and deep RL models of decision and planning. We will also delve into the methods and metrics for comparing such models to real-world neural data, and address how unsolved open problems in AI (that you can work on!) will drive forward novel neural models. Some meaningful background in modern neural networks is highly advised (e.g. CS229, CS230, CS231n, CS234, CS236, CS 330), but formal preparation in cognitive science or neuroscience is not needed (we will provide this).