Mastering Artificial Intelligence

CHAPTER 1:INTRODUCTION

• In this course you will learn to implement mathematical ideas in machine learning. You will investigate the process of learning and understand the application of various learning algorithms.
• Prerequisites:
  The courses assignments and notes will use python programming language and expects a basic knowledge of python. We assume the student has completed the Machine Learning Foundations or has an equivalent fluency in mathematics and fundamentals.

CHAPTER 2: LINEAR MODELS

• Understand linear approximation and modelling of problems and develop linear models

CHAPTER 3: DIMENSIONALITY REDUCTION

• Use ideas from linear algebra to transform dimensions and warp space providing additional flexibility and functionality to linear models.

CHAPTER 4:SVM

• Develop and implement kernel based methods to develop nonlinear models to solve few complex tasks.

CHAPTER 5:NEAREST NEIGHBOURS, K-MEANS, AND GAUSSIAN MIXTURE MODELS

• Review pattern recognition ideas with distance and cluster based models to understand similarity measures and grouping criteria.

CHAPTER 6:NAIVE BAYES AND DECISION TREES

• Dive into applications of bayes theorem and the use of decision criteria when learning from data.

CHAPTER 7:SEARCH

• Look at search from the perspective of graphs, trees and heuristic based optimizations.

CHAPTER 8:LOGIC AND PLANNING

• Discover ways to encode logic and develop agents that plan actions in an environment.

CHAPTER 9:REINFORCEMENT LEARNING AND HIDDEN MARKOV MODELS

• Engineering agents that learn from a sequence of actions using rewards and penalties.

CHAPTER 10:Q-LEARNING AND POLICY GRADIENT

• Operate in a stateful world over value and policy approximations tasks

>> Read more >>