Res.9-003 Brains, Minds and Machines
Res.9-003 Brains, Minds and Machines (Summer 2015, MIT OCW). Instructors: Prof. Tomaso Poggio (Course Director, MIT) and Prof. Gabriel Kreiman (Course Director, Harvard). This course explores the problem of intelligence - its nature, how it is produced by the brain and how it could be replicated in machines - using an approach that integrates cognitive science, which studies the mind; neuroscience, which studies the brain; and computer science and artificial intelligence, which study the computations needed to develop intelligent machines.
(from ocw.mit.edu
Lecture 25 - Andrei Barbu - From Language to Vision and Back Again
VIDEO
Instructor: Andrei Barbu. Using higher level knowledge to improve object detection, language-vision model that simultaneously processes sentences and recognizes image objects and events, performing tasks like image/video retrieval, generating descriptions, and question answering.
Go to the Course Home
Unit 1. Neural Circuits of Intelligence
Lecture 01 - Nancy Kanwisher - Human Cognitive Neuroscience
Lecture 02 - Gabriel Kreiman - Computational Roles of Neural Feedback
Lecture 03 - James DiCarlo - Neural Mechanisms of Recognition, Part 1
Lecture 04 - James DiCarlo - Neural Mechanisms of Recognition, Part 2
Lecture 05 - Winrich Freiwald - Primates, Faces, and Intelligence
Lecture 06 - Matt Wilson - Hippocampus, Memory, and Sleep, Part 1
Lecture 07 - Matt Wilson - Hippocampus, Memory, and Sleep, Part 2
Lecture 08 - Larry Abbott - Mind in the Fly Brain
Unit 2. Modeling Human Cognition
Lecture 09 - Josh Tenenbaum - Computational Cognitive Science, Part 1
Lecture 10 - Josh Tenenbaum - Computational Cognitive Science, Part 2
Lecture 11 - Josh Tenenbaum - Computational Cognitive Science, Part 3
Unit 3. Development of Intelligence
Lecture 12 - Liz Spelke - Cognition in Infancy, Part 1
Lecture 13 - Liz Spelke - Cognition in Infancy, Part 2
Lecture 14 - Alia Martin - Developing an Understanding of Communication
Lecture 15 - Laura Schulz - Children's Sensitivity to Cost and Value of Information
Lecture 16 - Jessica Sommerville - Infants' Sensitivity to Cost and Benefit
Lecture 17 - Josh Tenenbaum - The Child as Scientist
Lecture 18 - Debate: Tomer Ullman and Laura Schulz
Unit 4. Visual Intelligence
Lecture 19 - Shimon Ullman - Development of Visual Concepts
Lecture 20 - Shimon Ullman - Atoms of Recognition
Lecture 21 - Aude Oliva - Predicting Visual Memory
Lecture 22 - Eero Simoncelli - Probing Sensory Representations
Lecture 23 - Amnon Shashua - Applications of Vision
Unit 5. Vision and Language
Lecture 24 - Boris Katz - Vision and Language
Lecture 25 - Andrei Barbu - From Language to Vision and Back Again
Lecture 26 - Patrick Winston - Story Understanding
Lecture 27 - Tom Mitchell - Neural Representations of Language
Unit 6. Social Intelligence
Lecture 28 - Nancy Kanwisher - Introduction to Social Intelligence
Lecture 29 - Ken Nakayama - The Social Mind
Lecture 30 - Rebecca Saxe - MVPA: Window on the Mind via fMRI, Part 1
Lecture 31 - Rebecca Saxe - MVPA: Window on the Mind via fMRI, Part 2
Unit 7. Audition and Speech
Lecture 32 - Josh McDermott - Introduction to Audition, Part 1
Lecture 33 - Josh McDermott - Introduction to Audition, Part 2
Lecture 34 - Nancy Kanwisher - Human Auditory Cortex
Lecture 35 - Hynek Hermansky - Auditory Perception in Speech Technology, Part 1
Lecture 36 - Hynek Hermansky - Auditory Perception in Speech Technology, Part 2
Lecture 37 - Panel - Vision and Audition
Unit 8. Robotics
Lecture 38 - Russ Tedrake - MIT's Entry in the DARPA Robotics Challenge
Lecture 39 - John Leonard - Mapping, Localization, and Self-Driving Vehicles
Lecture 40 - Tony Prescott - Control Architecture in Mammals and Robots
Lecture 41 - Stefanie Tellex - Human-Robot Collaboration
Lecture 42 - Giorgio Metta - Introduction to the iCub Robot
Lecture 43 - iCub Team - Overview of Research on the iCub Robot
Lecture 44 - Panel: Robotics
Unit 9. Theory of Intelligence
Lecture 45 - Tomaso Poggio - iTheory: Visual Cortex and Deep Networks
Lecture 46 - Surya Ganguli - Statistical Physics of Deep Learning
Lecture 47 - Haim Sompolinsky - Sensory Representations in Deep Networks