Machine Learning

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!

Grab it

COURSE OUTLINE: The scientific discipline of Machine Learning focuses on developing algorithms to find patterns or make predictions from empirical data. It is a classical sub-discipline within Artificial Intelligence (AI). The discipline is increasingly used by many professions and industries to optimize processes and implement adaptive systems. The course places machine learning in its context within AI and gives an introduction to the most important core techniques such as decision tree-based inductive learning, inductive logic programming, reinforcement learning and deep learning through decision trees.

Syllabus

Introduction to the Machine Learning Course.
Foundation of Artificial Intelligence and Machine Learning.
Intelligent Autonomous Systems and Artificial Intelligence.
Characterization of Learning Problems.
Objects, Categories and Features.
Feature related issues.
Forms of Representation.
Decision Trees.
Bayes (ian) Belief Networks.
Artificial Neural Networks.
Genetic algorithm.
Inductive Learning based on Symbolic Representations and Weak Theories.
Generalization as Search - Part 01.
Generalization as Search - Part 02.
Decision Tree Learning Algorithms - Part 01.
Decision Tree Learning Algorithms - Part 02.
Instance Based Learning - Part 01.
Instance Based Learning - Part 02.
Machine Learning enabled by Prior Theories.
Explanation Based Learning.
Inductive Logic Programming.
Reinforcement Learning - Part 01 Introduction.
Reinforcement Learning - Part 02 Learning Algorithms.
Reinforcement Learning - Part 03 Q - Learning.
Fundamentals of Artificial Neural Networks - Part1.
Fundamentals of Artificial Neural Networks - Part2.
Perceptrons.
Model of Neuron in an ANN.
Learning in a Feed Forward Multiple Layer ANN - Backpropagation.
Recurrent Neural Networks.
Hebbian Learning and Associative Memory.
Hopfield Networks and Boltzman Machines - Part 1.
Hopfield Networks and Boltzman Machines - Part 2.
Convolutional Neural Networks - Part 1.
Convolutional Neural Networks - Part 2.
Tools and Resources.
Interdisciplinary Inspiration.