Fundamentals of Machine Learning (FunML)

(3-0-0-3)

CMPE Degree: This course is Selected Elective for the CMPE degree.

EE Degree: This course is Selected Elective for the EE degree.

Lab Hours: 0 supervised lab hours and 0 unsupervised lab hours.

Technical Interest Groups / Course Categories: Threads / ECE Electives

Course Coordinator: Ghassan AlRegib

Prerequisites: (MATH 2550 [min C] or MATH 2551 [min C] or MATH 2X51 [min T]) and (CS 1301 [min C] or CS 1371 [min C])

Catalog Description

An introduction to the fundamentals and applications of Machine Learning. Students cannot receive credit for both ECE 4252 and CS 4641.

Textbook(s)

Course Outcomes

N/A

Strategic Performance Indicators (SPIs)

N/A

Topic List

  1. Overview
    1. History of Pattern recognition, Development of ANN
    2. Types of Learning i.e., Supervised, Semi-supervised, Weakly supervised, Un-supervised
    3. General features of a supervised learning system i.e. features, training/validation set, labels, model complexity and overfitting etc.
    4. Simple overview of Optimization
  2. Classification
    1. Algorithms: Nearest Neighbors, Logistic Regression, Decision Trees, Random Forest, SVM, ANN
    2. Classification Performance Evaluation
    3. A set of hands-on exercises on the GPU Cluster
  3. Regression
    1. Linear Regression
    2. Polynomial Regression
    3. Regularized Linear Models
    4. A set of hand-on exercises on the GPU Cluster
  4. Clustering
    1. Introduction
    2. Proximity Measures
    3. Similarity vs. Dissimilarity
    4. Distance Measures
    5. Common Clustering Methods
    6. Evaluating Clustering Performance
    7. Image Segmentation as a clustering problem
    8. A set of hand-on exercises on the GPU Cluster
  5. Neural Networks
    1. Introduction to Artificial Neural Network: Non-linearity, Activations, Losses
    2. ConvNets
    3. Boosting, Stacking, Bagging
    4. Transfer Learning
    5. Data Augmentation
    6. A set of hands-on exercises on the GPU Cluster
  6. Autoencoders
    1. Fully Connected autoencoders, Conv AE, VAE
    2. A set of hand-on exercises on the GPU Cluster
  7. Sequence Modeling
    1. RNNs
    2. GRUs and LSTMs
    3. Word embedding attention
  8. Data Efficient Learning
    1. Active Learning
    2. Self-supervised Learning
    3. Weakly supervised learning
  9. Advanced Topics
    1. Explainability (XAI)
    2. Uncertainty Estimation
    3. Anomaly Detection
    4. Robustness in Neural Networks