Foundations of Neural Network Theory
4.0
creditsAverage Course Rating
Introduction to continuous mathematics for cognitive science, with applications to biological and cognitive network models: real and complex numbers, differential and integral multi-variable calculus, linear algebra, dynamical systems, numerical optimization. Recommended course background in Calculus I. This is a basic-level course not appropriate for students with significant math background. tudents who have completed both Calc III (AS.110.202 or AS.110.211) and Linear Algebra (AS.110.201 or AS.110.212 or EN.553.291) or an equivalent combination may not register. Also offered as AS.050.672.
Spring 2015
Professor: Paul Smolensky
The best aspects of the course included the interesting subject area, the broad exposure to theories and debates in neural network theory, and the freedom to apply topics covered to areas of interest. Students enjoyed the professor’s fun and enlightening lectures. While, some students enjoyed the inclusion of math into theory, others found the math component to be intimidating. Further, while the syl abus was coherent and productive, the workload was often overwhelming. This course would benefit from having more practice available for math problems and help sessions outside of class. Prospective students should know they need a basic understanding of calculus and linear algebra prior to taking this course. 83