Machine Learning for Java Developers

Course Description 

Machine Learning is an extremely popular field both of researchers as well as programmers. After spending several years programming and building application machine learning acts as a natural area where you would like to evolve to.

This course starts by building basic concepts on what machines learning is and how machines learn. You built your very own learning model in Java from scratch and improve it as you learn more concepts.

You learn about Regression, Classification and Clustering algorithms – the most popular ones being used.

Then the course moves on to learning how distributed machine learning works. You use out of the box algorithms available  on Apache Spark to train, test and deploy your learning models.

While this is not a comprehensive course, after doing this you will be able to solve 80% of problem you face in developing Machine learning algorithms.

Curriculum 
  1.  Module I: Machine Learning Basic
    1. Introduction to Artificial Intelligence
    2. What is Machine Learning
    3. Review of Mathematics
      1. Matrices and vector
      2. Differentiation
    4.  Writing your first Machine Learning Algorithm
      1. Working with Data and Files
      2. Matrix method
      3. Loss based Methods
      4. Gradient Descent
      5. Saving and Reusing your models
  2. Module II: Machine learning Ecosystem
    1. Concepts
      1. Parameters an Hyper Parameters
      2. Regularization
      3. Data Normalization
      4. Loss Functions
      5. Probability Theory
      6. Maximum Likelihood Estimation
    2. Working with Popular Datasets
      1. CIFAR Dataset for Image Recognition
    3. Popular Machine Learning algorithmson
      1. Logistic Regression
      2. Clustering
      3. Decision Trees
      4. Support Vector Machines
      5. K Nearest Neighbor
      6. Random Forests
  1. Distributed machine learning using Apache Spark
    1. What is Apache Spark
    2. Setting up Apache Spark cluster
    3. Data Types
    4. Linear regression
    5. Logistic regression
    6. Support Vector Machines
    7. Classification
    8. Random Forests
  1. Case Studies
    1. Image Recognition with CIFAR Dataset
    2. Price prediction 
  2. Conclusion
    1. Getting help in future
    2. Taking it from here
  3. Acknowledgement and citations
What are the requirements? 
  • Experience with programming in Java Language
  • Basic understanding of String and File operations using Java Language
  • Familiarity with Eclipse development environment
What am I going to get from the course? 
  • Understanding of How Machines Learn
  • Ability to write a Machine learning algorithm from scratch in Java
  • Get acquainted with Machine Learning concepts and popular algorithms
  • Expertise on how to install and configure Apache Spark to implement Distributed Machine Learning
  • Understand working with popular datasets
  • Ability to Train, Test and Deploy your own learning models
Who is the target audience? 
  • This course is meant for Java developers who want to learn Machine Learning and implement in their programs within a few hours
  • This course is NOT meant for people looking to get deeper understanding of Machine Learning algorithms, especially the mathematical and scientific portions of it
Lectures: 
3
Language: 
English
Includes: 

Basic concepts
Hands on learning
Reading material

Skill level: 
Basic
Duration: 
24 Hrs