| |
Jan 18, 2025
|
|
|
|
|
ECE 6356 - Introduction to Machine Learning Credit Hours: 3.00
Lecture Contact Hours: 3.0 Lab Contact Hours: 0.0
Prerequisite: This course lectures will frequently involve linear algebra. Therefore, you need to be familiar with basic linear algebra concepts, including vector, matrix, vector/matrix operations, linear independence, eigen decomposition, matrix inversion, matrix derivative, etc. You should be familiar with basic concepts in probability and statistics such as distribution, expectation, variance, and maximum likelihood estimation of a random variable. You should also know the basic of optimization theory such as gradient descent, local optimality, and convexity. We will have programming assignments. You should be familiar with either Python or Matlab.
Deep Learning; Convolutional Neural Network; Auto-Encoder; Generative Adversarial Network; Recurrent Network; Dictionary Learning and Sparse Coding; Dimensionality Reduction; Ensemble Learning; Classification; Regression; Feature Selection
Add to Portfolio (opens a new window)
|
|