Description
Material
Description

Machine Learning and deep learning are fast-growing areas. They are becoming a standard component of many engineering problems such as engineering in big data analytics. This course is to cater for the increasing needs for training students with the basic competency of understanding and applying machine learning and deep learning models.

Detailed course content

  • Introduction, regression
  • Classification (KNN, naive Bayes, decision trees, logistic regression, support vector machines (SVM), kernel methods)
  • Time series modeling, HMM
  • Model fitting, averaging, and selection
  • Unsupervised models, dimensionality reduction, clustering, EM algorithm
  • Introduction to neural networks, feed-forward networks, backpropagation
  • Recurrent neural networks (RNN), LSTM, GRU, sequence-to-sequence models
  • Convolutional neural networks (CNN)
  • Autoencoder
  • Popular deep learning platforms
  • Application of machine learning
Credit Breakdown

Lecture: 3
Lab: 0.25
Tutorial: 0.25

Academic Unit Breakdown

Mathematics 11
Natural Sciences 0
Complementary Studies 0
Engineering Science 20
Engineering Design 11

PREREQUISITE(S): ELEC 278 or CISC 235, ELEC 326, or permission of the instructor

EXCLUSION(S): CMPE 452