Academics

Graduate Program

Academics

Graduate Program

Graduate Program

Introduction to brain IT

Subject No.
Research
Credit
Classification
EE532
Signal
3
72

This course will discuss the key differences in architecture and algorithms between conventional information processing systems (e.g. von Neumann machines) and biological brains. Subsequently, we will try to come up with the scaffold of a basic design for a non-von Neumann type of brain-like information processing system.

Recommend

Computer, Communication, Signal
EE528

In this course, based on the fundamental concepts and knowledge addressed in EE210, we discuss advanced topics in probability and random processes for applications in engineering. Topics include algebra of sets, limit events, random vectors, convergence, correlation functions, independent increment processes, and compound processes. (Prerequisite: {EE210} or {Approval of the Instructor})

Introduce students the fundamental concepts and intuition behind modern machine learning techniques and algorithms, beginning with topics such as perceptron to more recent topics such as boosting, support vector machines and Bayesian networks. Statistical inference will be the foundation for most of the algorithms covered in the course.

 

This course deals with various matrix computation algorithms for signal processing such as linear system solving, matrix norm, positive-definite matrix. Toeplitz matrix, orthogonalization/diagonalization, eigenvalue problems, SVD (singular value decomposition), iterative methods for linear systems, and so on.