Machine Learning

This Pragra Program will be a technical look at machine learning with an understanding of key theory, models, and more advanced tools in machine learning solutions through a quantitative approach. The program is based on the Python programming language and makes extensive use of the TensorFlow machine learning framework. Machine Learning program is combination of three different levels:

 

Machine Learning Fundamentals

By the end of this track, you will have a sound understanding of what Machine Learning exactly is, along with a firm grasp on what Machine Learning can and cannot accomplish. Through hands-on examples, this track will also equip you with the key principles behind how models are built, evaluated and eventually put into production.

 

Intermediate Machine Learning

This track takes you to the next level in your Machine Learning journey, by lifting the hood and exposing you to how data is organized and streamlined for machine learning to actually work. We’ll also cover the most fundamental concept that underpins the model fitting process – gradient descent, before introducing one of the most profound developments in the field of AI -Deep Learning.

 

Advanced Machine Learning

We’ll look at a few state of the art AI implementations – especially generative modelling, with a couple of hands-on exercises where you’ll be building your own spam detector and sentiment analyzer. This track will also introduce advanced Deep Learning architectures such as CNN and RNN and equip you with essential tools to continue exploring and charting your path through the fascinating field of AI!

Training Schedule

Every Saturday from 02:00 PM to 4: 00 PM in room training
Every Wednesday – Online Session from 8:45 PM to 10:45 PM

Training Duration

5 Months Intensive Training Program.

Module 1: Machine Learning Fundamentals

  • Why the hype?
  • Relationship between Machine Learning & Artificial Intelligence
  • Building your first model
  • Types of Machine Learning models
  • Probability, Bayes Rule & Calculus
  • Getting started with Python
  • Data visualization basics
  • Statistical models
    – Linear Regression
    – Logistic Regression
    – Naive Bayes
    – Random Forest
    – KNN
    – SVM
  • Selecting the best model using cross validation
  • RESTifying your model for deployment

Module 2: Intermediate Machine Learning

  • Getting started with Numpy
  • “Garbage in, garbage out” – organizing your data
  • Ensemble Models
  • Data reduction techniques
    – Principal Component Analysis
  • Building an anomaly detector
  • How models learn – introducing gradient descent
  • Deep Learning Introduction & Fundamentals

Module 3: Advanced Machine Learning

  • Introduction to TensorFlow
  • Understanding generative and discriminative models
  • Natural Language Processig
    – Building a spam detector
    – Building a sentiment analyzer
  • Recurrent Neural Networks basics
  • Convolution Neural Networks basics
  • Further reading & references