In this course, we will follow Jeff Heaton's comprehensive “Deep Learning” curriculum. Deep learning is a field that offers exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as both input and output.
Deep learning allows a neural network to learn hierarchies of information in a way that is like the function of the human brain. This course will introduce you to classic neural network structures, Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN), and reinforcement learning.
Applications of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids.
Our course will be based on Jeff Heaton's following resources:
https://www.heatonresearch.com/course/
This link provides access to Jeff Heaton’s original course content, presentations, and additional resources.
https://github.com/jeffheaton/app_deep_learning
This GitHub repository contains code examples, exercises, and projects that we will use throughout the course. Students are recommended to fork this repository to their own accounts for easier tracking.
This course will cover the following topics: