Deep Learning
This page contains links to html renders of Jupyter Notebooks and Google Colab notebooks that I developed in Spring 2019 for the course DSCI 39001 - Neural Networks offered at Lindenwood University. These notes were used during the first time I taught the course, when I was less experienced with the field of deep learning. I would change many things the next time I taught the course. I would also consider moving all of the lecture material into Google Colab.
Disclaimer: These notebooks are not intended to be a standalone resource for machine learning. These were created to supplement lecture presentations. Many of the lessons (especially the later ones) would benefit from additional exposition.
Lecture Notebooks
- 01 - Introduction to Machine Learning
- 02 - The Artificial Neuron
- 03 - Introduction to Neural Networks
- 04 - Designing Neural Networks
- 05 - Forward Propagation with Matrices
- 06 - MNIST Dataset
- 07 - Regression and Regularization
- 08 - MNIST CNN
- 09 - Fashion MNIST
- 10 - Google Colab Test
- 11 - Training a CNN using GPU
- 12 - CIFAR10
- 13 - Data Generators
- 14 - Fit Generator
- 15 - Fine-Tuning a CNN
- 16 - Data Augmentation
- 17 - Transfer Learning
- 18 - Back Propagation
- 19 - Recurrent Neural Networks
- 20 - RNN for Time Series
- 21 - LSTM Example
- 22 - Sentiment Analysis with RNNs
- 23 - Word Embeddings
- 24 - GloVe
- 25 - Text Generation