Convex Optimization for Machine Learning
|
Published in Now Publishers (open access)
Developed during the past three years while teaching EE523 Convex Optimization and EE424 Introduction to Optimization.
The contents are tailored to modern applications in machine learning and deep learning.
This book includes programming implementation of a variety of machine learning algorithms inspired by optmization fundamentals.
The implementation is based on Python, CVXPY and TensorFlow, and a brief tutorial of the used programming tools is also provided.
This book serves as a textbook mainly for a senior-level undergraduate course, yet is also suitable for a first-year graduate course.
Supported by the Google Education Grant
|
Communication Principles for Data Science
|
Published in Springer
Developed during the past eight years while teaching EE321 Communication Engineering four times
This book makes an explicit connection between communiation and data science problems, as well as to succinctly deliver the story of how communication principles play a role in trending data science applications such as community detection, DNA sequencing, speech recognition, and machine learning.
It includes programming implementation of a variety of algorithms inspired by fundamentals.
The implementation is based on Python and TensorFlow, and a brief tutorial of the used programming tools is also provided.
This book serves as a textbook for a junior and senior-level undergraduate course.
|
Information Theory for Data Science
|
Will be published (Now Publishers)
Developed during the past nine years while teaching EE623 Information Theory (seven times) and EE326 Introduction to Information Theory and Coding (twice).
The contents are tailored for recent and trending topics in data science such as social networks, ranking, GANs and fair machine learning.
This book includes programming implementation of a variety of algorithms inspired by fundamentals.
The implementation is based on Python and TensorFlow, and a brief tutorial of the used programming tools is also provided.
This book serves as a textbook mainly for a senior-level undergraduate course, yet is also suitable for a first-year graduate course.
Supported by the Google Education Grant
|
Probability for Information Technology
A preliminary version (to be published)
Developed during 2021 Spring semester while teaching EE210 Probability and Introductory Random Processes
This book succinctly relates the ‘‘story’’ of how the key principles of probability play a role, via classical and trending IT applications such as communication, social networks, machine learning and speech recognition.
The probabilistic concepts are delivered through many running examples, killer applications and Python coding exercises.
This book serves as a textbook for a sophomore-level undergraduate course, yet is also suitable for a junior or senior-level undergraduate course.
|