Neural Computation Course ID 15686 Description Computational neuroscience is an interdisciplinary science that seeks to understand how the brain computes to achieve natural intelligence. It seeks to understand the computational principles and mechanisms of intelligent behaviors and mental abilities -- such as perception, language, motor control, and learning -- by building artificial systems and computational models with the same capabilities. This course explores how neurons encode and process information, adapt and learn, communicate, cooperate, compete and compute at the individual level as well as at the levels of networks and systems. It will introduce basic concepts in computational modeling, information theory, signal processing, system analysis, statistical and probabilistic inference. Concrete examples will be drawn from the visual system and the motor systems, and studied from computational, psychological and biological perspectives. Students will learn to perform computational experiments using Matlab and quantitative studies of neurons and neuronal networks. Key Topics Artificial intelligence, Neuro-inspired AI, Computational Neuroscience Required Background Knowledge calculus, statistics, linear algebra, Course Relevance This course is for masters students. Undergraduates should enroll in 15-386. Course Goals Artificial intelligence, Neural mechanisms underlying perception and intelligence. Neuro-inspired AI, Computational Neuroscience Learning Resources Mostly online resources, classical and current articles in the field. Assessment Structure Homework 60%, Participation and Journal Club 10%, Midterm 10%, Final 20% Extra Time Commitment Friday journal club Course Link http://www.ni.cmu.edu/~tai/nc24.html
