CSE590/MB590 Special Topics
  - Machine learning

Topics included: AI, Machine Learning and Deep Learning; Supervised Learning; Unsupervised Learning; Reinforcement Learning; Regression; Classification; Clustering; Dimensionality Reduction; Single Layer Perceptron; Multi-Layer Perceptron and Deep Learning.
  • » 23 hours in class lecturing plus dedicated mentoring sessions from our faculty of industry experts


  • » 1.5 semester credits for both certificate and master’s degree


  • » Access to high-quality live class recording


  • » Online live classroom available for all classes


  • » Lifetime learning resources for our students


  • $ 1000
Unit 1: Overview
Introduction
  • AI: Machine Learning and Deep Learning
  • Supervised Learning
  • Unsupervised Learning
  • Reinforcement Learning
  • Regression
  • Classification
  • Clustering
  • Dimensionality Reduction
  • Single Layer Perceptron
  • Multi-Layer Perceptron and Deep Learning
Frameworks
  • General Purpose Frameworks
  • Deep Learning Frameworks
  • Comparison of popular Frameworks
  • Basics of TensorFlow
  • PyTorch as alternate
Building a Deep Learning Application
  • Introduction to ‘R’
  • Using ‘R’ in Collaboratory
  • Housing price prediction
Unit 2: Applied Theory
Introduction
  • What are datasets
  • Data analysis
  • The Model: parameters and hyperparameters
  • Activation Functions
  • Loss Functions
  • Learning Algorithms
  • Accuracy
  • Generalization
  • Regularization and Dropout
Mid Term Projects
  • Regression Example: Polynomial Regression
  • Classification Example: Logistic Regression
Unit 3: Deep Learning
Introduction
  • What is Deep Learning
  • Building a deep learning network
  • Improving a deep neural network
    • Debugging Underfitting and Overfitting
    • Adding/deleting layers
    • Regularization and Dropout
    • Optimization
    • Regularization
  • Feed Forward Neural Network
    • FFNN Applied Theory
    • FFNN projects
      • Binary Classifier
      • Multiclass Classifier
  • Convolution Neural Networks
    • CNN Applied Theory
    • CNN Example - GoogleNet
    • CNN Projects
      • Hand digit recognition
      • Object Detection
  • Recursive Neural Network
    • Applied Theory
    • Min Char RNN
  • Generative Models
    • Applied Theory
    • Generative Adversarial Networks
    • Building GAN using MNIST example
    • PixelRNN (2016) and PixelCNN (2016)
    • Sample GAN Project
Your Instructor
 Rohit Sharma
Rohit Sharma is an engineer, author and entrepreneur. He founded 2 companies, architect of several software products, published 2 best seller books and over 10 papers in international conferences and journals. He has contributed to electronic design automation domain for over 20 years learning, improvising and designing solutions. He is passionate about many technical topics including machine learning and VLSI analysis and modeling.