Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 375 AI for Science & Health ★★★★☆

Core course · AI for Science & Health

Large-Scale Neural Network Modeling for Neuroscience (PSYCH 249)

中文:面向神经科学的大规模神经网络建模

Model the brain with large-scale neural networks: vision, audition, motor control, language, and decision-making as convergent evolution.

Draft translation: official facts are checked; wording may change after native review.

3 units Winter 2027 Letter (ABCD/NP) ★★★★☆
NeuroAIComputational neuroscienceAI4Science

Course positioning

Taught by Dan Yamins, CS 375 (PSYCH 249) is a core course at the intersection of computational neuroscience and AI. It discusses how the internal components of artificial networks correspond to real brain structure, covering feedforward perception, recurrent dynamics, attention/memory/navigation, language Transformers, self-supervision, and deep RL, and teaches how to quantitatively compare models with neural data.

What it covers

  1. Feedforward perception models: vision, audition, somatosensation
  2. Recurrent networks: dynamics, motor control
  3. Attention/memory/navigation: integrated models
  4. Language and Transformers: modeling language areas
  5. Self-supervised learning: comparison with brain learning
  6. Deep RL: decision-making and planning
  7. Model-neural data comparison: RSA, encoding models, metrics
  8. Project

Prerequisites

Modern neural network background (one of CS 229/230/231N/234/236/330); no cognitive science/neuroscience background required.

Assessment & workload

Paper discussion plus a project. Check the current syllabus for details.

Who it's for

NeuroAI, computational neuroscience, and AI interpretability; people who want to use AI to understand the brain.

Study advice

Take CS 231N or CS 224N first. Pair with CS 322/EE 292R for a broader view.

Related courses

Official course description

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).