https://github.com/ehvenga/ece565

ECE565 - Machine Learning : Assignments and Coursework
https://github.com/ehvenga/ece565

datascience jupyter-notebook machine-learning python regression

Last synced: about 1 month ago
JSON representation

ECE565 - Machine Learning : Assignments and Coursework

• Host: GitHub
• URL: https://github.com/ehvenga/ece565
• Owner: ehvenga
• Created: 2024-02-09T10:02:50.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-03-26T04:44:47.000Z (10 months ago)
• Last Synced: 2024-11-30T05:29:12.272Z (about 1 month ago)
• Topics: datascience, jupyter-notebook, machine-learning, python, regression
• Language: Jupyter Notebook
• Homepage:
• Size: 1.23 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# ECE565 - Machine Learning

## Course Overview

This course, ECE565, delves into the theory, design, and engineering applications of Machine Learning (ML), with a special emphasis on computational intelligence. It explores the implementation of ML concepts using embedded hardware platforms, high-performance libraries, and architectures. The curriculum includes an in-depth examination of various ML algorithms, including Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs), and is cross-listed as ECE 565.

### Instructor

Dr. Mohammad Imtiaz

## Course Objectives

By the end of this course, students will:

1. Grasp fundamental concepts of Machine Learning.

2. Learn mathematical and statistical theories/tools essential for ML.

3. Understand the main ML algorithms.

4. Comprehend the steps involved in data acquisition.

5. Master data pre-processing techniques for ML.

6. Gain insights into ML algorithms and their real-world applications.

7. Understand the foundations of neural networks and deep learning.

8. Explore major NN and DNN architectures.

9. Implement NN and DNN on various hardware architectures.

## Course Topics

- Mathematical and Statistical Tools for ML

- Data Pre-processing Techniques

- Foundations of Neural Networks (Perceptron, Multi-Layer Feed-Forward Networks, Backpropagation, etc.)

- Deep Neural Networks (DNNs)

- Convolutional Neural Networks (CNNs)

- Recurrent Neural Networks (RNNs)

- Recursive Neural Networks

- Autoencoders

- Hardware for NN Deployment

## Repository Structure

This repository contains lecture notes, assignment templates, project starter codes, and additional resources to aid in the understanding and application of Machine Learning concepts covered in ECE565. The contents are organized as follows:

- `/lectures` - Lecture notes and slides.

- `/assignments` - Assignment descriptions, templates, and submission guidelines.

- `/projects` - Project descriptions, starter codes, and resources.

- `/resources` - Additional resources, reading materials, and useful links.

## Usage

```bash

git clone https://github.com/ehvenga/ece565.git

```