## Introduction to Machine Learning and Data Analysis

SEE SCHEDULE### Duration: 5 Days

### Method: Hands On, Instructor led

### Price: $2975.00

### Course Code: ML1000

## Audience

Developers and Managers with a programming background interested in Machine Learning for Data Analysis

## Description

Machine learning is a popular artificial intelligence based technique where advanced algorithms are used create predictive models that can learn from existing data so that not only we can analyze existing data but the created models can be used to predict future behaviors, outcomes, and trends. This course covers many important concepts, theory and algorithms in machine learning. Practical programming examples are provided on real datasets so that the underlying concepts can be nicely understood. All necessary Math background is explained in an intuitive easy to understand manner. Some of the programming examples use C#, but most of the coding is done in Python where Machine learning libraries such as Theano, Tensor Flow and CNTK are used.

## Objectives

Upon successful completion of this course, the student will be able to:

- Understand the different machine learning(ML) concepts and algorithms
- Program different ML algorithms in Python
- Effectively use different ML libraries for classification and data analysis problems
- Understand the new emerging ML techniques

## Prerequisites

Some programming background in an Object-Oriented Language such as C#, Java, or Python.

## Topics

- I. Analyzing Data Dimensions
- Visualizing datasets, Eigen values and Eigen Vectors for data analysis
- Principle Component Analysis for dimensionality reduction
- Analyzing customer data using Principle Component Analysis
- Example of face recognition using Principal Components and Eigen Faces

- II. Clustering Data
- K-means, K-means++ and K-medoids algorithms
- Gaussian mixture models. Applying clustering to practical data problems such as customer behaviors

- III. Classification of Data
- Decision trees, KNN classifiers, Random forests, Bagging and Boosting
- Example of Adaptive boosting for face detection
- Support Vector Machines

- IV. Regression Analysis
- Estimating coefficients of a regression model
- Fitting noisy data using RANSAC
- Decision tree regression
- Random forest regression

- V. Artificial Neural Networks for Classification
- Feed forward Networks, training neural networks using back propagation algorithm, preventing overfitting using regularization and drop out
- Creating Neural Networks for data classification

- VI. Machine Learning for Text Classification
- Bag of Words model, transforming words into features, term frequency-inverse document frequency
- Applying machine learning for sentiment analysis

- VII. Introduction to Deep Networks
- Deep Convolution Networks for Image classification
- Example of a deep CNN for MNIST character recognition

- VIII. Overview of Deep Learning Models
- Recurrent Neural Networks
- Mixture of Experts for data classification
- Q-Learning and Reinforcement Learning