MATH 4700 Journal

This is a collection of the knowledge I have accumulated accumulated over an independent learning semester covering topics in machine learning with a focus on deep learning and neural networs. The purpose of this journal twofold: to conserve the knowledge acquired and as the Final Project for the course. The following is a list of the topics covered in the course:

Chapter 1 - Basics of Machine Learning

1. Introduction to Machine Learning
2. Loss functions
3. Tensors and Multivariate Calculus

Chapter 2 - Neural Networks

1. Introduction to Neural Networks
2. How to train Neural Networks - Optimization
3. Good practices for Neural Networks
4. Convolutional Neural Networks
5. Autoencoders
6. Recurrent Neural Networks and Beyond

Chapter 3 - Other Machine Learning Topics

1. Decision Trees
2. Ensemble Methods
3. Gaussian Mixture Models

Note that this isn’t my first time dealing with machine learning, as such some of the more basic topics are not covered in detail or outright omitted.

For time constraints the section about Recurrent Neural Networks, LSTM and Transformers are not available yet.