Brain-like computation and intelligence

NX-414 / 5 credits

Teacher(s): Mathis Alexander, Schrimpf Martin

Language: English

Summary

Recent advances in machine learning have contributed to the emergence of powerful models of animal perception and behavior. In this course we will compare the behavior and underlying mechanisms in these models as well as brains.

Content

This comparison will be done based on contemporary models of vision, audition, touch, proprioception, motor control, language, and cognition.

Content

  • Classical models of sensory, motor and cognitive function

  • Goal-driven and data-driven brain modeling

  • Hierarchical and recurrent neural network models

  • Comparing models to neural data

  • Comparing modes to behavioral data

  • Modern tools for quantifying behavior

Keywords

Python, NeuroAI, Deep Learning, Perception, Behavior, Motor Control and Learning

Learning Prerequisites

Recommended courses

CS-433 (strongly recommended)

Important concepts to start the course

Programming in Python, good mathematics and machine learning background

Learning Outcomes

By the end of the course, the student must be able to:

  • Formulate models of brain function
  • Hypothesize potential mechanisms that give rise to behavior
  • Design models of brain functions
  • Characterize current models of brain function

Transversal skills

  • Set objectives and design an action plan to reach those objectives.
  • Demonstrate the capacity for critical thinking
  • Write a scientific or technical report.
  • Summarize an article or a technical report.

Teaching methods

Lectures and exercises to discuss and work on problem sets (both numerical and analytical). There will be one project as part of this class, which is partially done outside of the classroom.

 

Expected student activities

Attend lectures and take notes during lectures, participate in quizzes and read scientific articles. Solve the problem sets and take the final exam.

Assessment methods

The final mark is a combination of three evaluations: class project (30%), quizzes (20%), final exam (50%).

Supervision

Office hours Yes
Assistants Yes
Forum Yes

Resources

Virtual desktop infrastructure (VDI)

No

Moodle Link

In the programs

  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: mandatory
  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: mandatory
  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: Written (summer session)
  • Subject examined: Brain-like computation and intelligence
  • Lecture: 2 Hour(s) per week x 14 weeks
  • Exercises: 2 Hour(s) per week x 14 weeks
  • Type: optional

Reference week

Related courses

Results from graphsearch.epfl.ch.