Machine Learning

Course Objectives: This course on Machine Learning will explain how to build systems that learn and adapt using real-world applications (such as robotics and brain wave signal understanding). Some of the topics to be covered include reinforcement learning, neural networks, genetic algorithms and genetic programming, parametric learning (density estimation), clustering, and so forth. The course will be project-oriented, with emphasis placed on writing software implementations of learning algorithms applied to real-world problems.

Course Outline:

Introduction to Machine Learning
Linear Regression with one Variable
Multivariate Linear Regression.
Regularizes, Learning curves
Optimization
Classification: Linear classification
Support Vector Machines
Kernels
Neural Network: Representation
Neural Network: Learning, Back-propagation
Convolutional Neural Network
Unsupervised Learning: Clustering
Anomaly Detection
Project Presentations

Practice with PYTHON:

Basics of PYTHON
Reading and manipulate a data by Pandas
Arrays and Normal Equation
Linear/Logistic regression
Preprocessing the data for ML Algorithms
Classification - MINST dataset
NLP simplified

TextBook: T. Mitchell, Machine Learning, McGraw-Hill

Laboratory: PYTHON

Course Evaluation Method

Project 40%

Quiz 2 x 5%

Lab Assignment 5 x 2%

Final Exam 40%

Report abuse