ENEL645 - Data Mining & Machine Learning

Short coruse description: Types of data mining: classification, clustering, association, prediction. Processes: data preparation, model building. Techniques: decision tree, neural network, evolutionary computing, Bayesian network. Applications: multi-media, text and web mining.

We will be using Python 3 with TensorFlow.

Tutorials

Week 01

• Tutorial 01: Introduction to Python
• Tutorial 02 Introduction to NumPy
• Tutorial 2.1 Avoid loops!

Week 02

• Tutorial 03: Model Selection, Overfitting and Regularization

Week 03

• Tutorial 04: Fully Connected Neural Networks - synthetic
• Tutorial 05: Fully Connected Neural Networks - MNIST
• Optional:
  • Tutorial 06: Softmax, one-hot-encoding, loss functions
  • Tutorial 07: Fully Connected Neural Networks - revisited

Week 04

• Tutorial 08: CNNs - MNIST
• Tutorial 09: CNNs - Gender Classification

Week 05

• Tutorial 10: Transfer Learning - Garbage Classification

Week 06

• Tutorial 11: Fully Convolutional Neural Network - Denoising
• Tutorial 12: Medical Image Segmentation - UNET

Week 07

• Reading week

Week 08

• Tutorial 13: AutoML

Week 09

• Tutorial 14: Alzheimer's Classification - Pitfalls whend esigning CNN models

Week 10

• Tutorial 15: Traditional Machine Learning - Predicting loan defafults

Week 11

• Tutorial 16: Recurrent Neural Networks - Next Frame Predictions

Week 12

• Tutorial 17: Generative Adversarial Networks
• Tutorial 18: Generative Adversarial Networks

Assignments

• Assignment 01 - option 01: Garbage Classification System
• Assignment 01 - option 02: Python/NumPy Programming
• Assignment 02: Paper Reading
• Assignment 03: Coding