Course Code: matlabds
Duration: 35 hours
Prerequisites:
  • Knowledge of basic mathematical concepts such as linear algebra, probability theory and statistics
  • No previous experience with MATLAB is needed
Overview:

In the first part of this training, we cover the fundamentals of MATLAB and its function as both a language and a platform.  Included in this discussion is an introduction to MATLAB syntax, arrays and matrices, data visualization, script development, and object-oriented principles.

In the second part, we demonstrate how to use MATLAB for data mining, with a focus on data modeling and machine learning.

Throughout the course, participants will put into practice the ideas learned through hands-on exercises in a lab environment. By the end of the training, participants will have a thorough grasp of MATLAB's capabilities and will be able to employ it for solving real-world data science problems.

Assessments will be conducted throughout the course to gauge progress.

Format of the course

  • Course includes theoretical and practical exercises, including case discussions, sample code inspection, and hands-on implementation.
Course Outline:

Introduction
MATLAB for data mining

Part 01: MATLAB fundamentals

Overview
MATLAB for data analysis, visualization, modeling, and programming.

Working with the MATLAB user interface

Overview of MATLAB syntax

Entering commands
Using the command line interface

Creating variables
Numeric vs character data

Analyzing vectors and matrices
Creating and manipulating
Performing calculations

Visualizing vector and matrix data

Working with data files
Importing data from Excel spreadsheets

Working with data types
Working with table data

Automating commands with scripts
Creating and running scripts
Organizing and publishing your scripts

Writing programs with branching and loops
User interaction and flow control

Writing functions
Creating and calling functions
Debugging with MATLAB Editor

Applying object-oriented programming principles to your programs

Part 02: MATLAB for Data Mining

Overview
MATLAB for data mining, machine learning and predictive analytics

Using the Statistics and Machine Learning Toolbox

Accessing data
Obtaining data from files, spreadsheets, and databases
Obtaining data from test equipment and hardware
Obtaining data from software and the Web

Preprocessing the data (reduction, transformation, feature extraction)
Principal Component Analysis (PCA) and Partial Least Squares (PLS)

Exploring the data
Identifying trends, testing hypotheses, and estimating uncertainty

Segmenting the data
Clustering with K-means

Regression Analysis

Machine learning
Supervised and unsupervised machine learning algorithms

Creating customized algorithms

Modeling the data

Generating .mat files

Creating visualizations

Publishing reports

Sharing analysis tools
As MATLAB code
As standalone desktop or Web applications

Summary and closing remarks