Syllabus

Course Meeting Times

This course met for an intensive 3 week period, with a mix of lecture, tutorial and project work segments.

Course Overview

This course introduces you to the scientific study of intelligence in brains and machines. Through lectures by leading researchers in the field, you learn about the theoretical foundations and computational methods used in intelligence research; empirical methods used in neuroscience and cognitive science to probe the function of neural circuits and emergent behavior; the kinds of questions that can be addressed with computational and empirical methods and how the integration of multiple perspectives can accelerate the pace of intelligence research. This foundation is enriched through the exploration of current research on a range of topics including visual recognition, audition and speech, natural language understanding, robotics and motor control, cognitive development, social cognition, machine learning and Bayesian inference, and visual and spatial memory. These topics are organized into curricular units that are somewhat independent, allowing flexibility in the order and extent to which the topics are studied. Resources are also provided to support hands-on computer activities to study methods of modeling and data analysis in greater depth.

The materials in this open-licensed OCW resource come from the 2015 version of the Brains, Minds and Machines Summer Course. Additional materials, including from later years, are at the Brains, Minds and Machines Summer Course website.

Prerequisites and Preparation

This course for graduate students and advanced undergraduates is intended for people with basic knowledge in the following areas, at an undergraduate level:

  • Mathematics: Calculus, linear algebra, probability and statistics
  • Computation: Introduction to computer programming, machine learning
  • Introduction to neuroscience
  • Introduction to psychology or cognitive science

Lectures vary in the depth of background needed to understand the main concepts and results. Some lectures are accessible to a broad audience, while others require deeper background in areas such as mathematics or machine learning. Useful background is noted within each topical unit.

Course Components

This course consists of the following components:

  • Lectures
  • Tutorials
  • Readings
  • Project work

Lectures

Video lectures by faculty integrate historical background, instruction on computational and empirical methods, current research findings, and directions for future research. Additional seminars by guest speakers highlight exciting state-of-the-art research. Lecture slides are also provided.

Tutorials

Tutorials by faculty and postdoctoral associates introduce background material to support lectures and project work. Tutorials vary in their format, integrating a mix of video lectures, handouts, and resources to support hands-on computer work. The tutorials on MATLAB® Programming, Church Programming, and Machine Learning, include extensive programming exercises.

Readings

Readings for each unit and tutorial provide a combination of useful background to review in advance, and material for further study of topics covered in the lectures. This resource can also support activities such as group discussions, Journal Clubs, and writing assignments.

Project Work

Both the Brains, Minds and Machines summer course and the associated MIT course 9.523 Aspects of a Computational Theory of Intelligence (described in the Instructor Insights section) incorporate an extended research-like project experience carried out individually or in small groups. Descriptions of sample projects related to each unit are provided. For some projects, there are additional resources such as readings, code, and data. Video presentations highlight a few of the summer course projects.

Acknowledgements

We would like to thank Ellen Hildreth for adapting materials from the Brains, Minds, and Machines Summer Course and MIT course 9.523 for OCW students. We would also like to thank Kris Brewer for filming and editing all the lecture videos, and Daniel Zysman for assisting with the preparation of the MATLAB tutorial and project resources. Finally, we thank the dedicated teaching assistants, instructors, and guest speakers, for their many contributions to lectures, tutorials, and lab materials for this course.