This course covers foundational deep learning theory and practice. We begin with how to think about deep learning and when it is the right tool to use. The course covers the fundamental algorithms of deep learning, deep learning architecture and goals, and interweaves the theory with implementation in PyTorch.
Overview
Syllabus
- Introduction to Deep Learning
- Meet your instructor, get an overview of the course, and find a few interesting resources in this introductory lesson.
- Deep Learning
- This introductory lesson on Deep Learning covers how experts think about deep learning and how to know when deep learning is the right tool for the job, including some examples.
- Minimizing Error Function with Gradient Descent
- Beginning with PyTorch and moving into both Error Functions, Gradient Descent, and Backpropagation, this lesson provides an overview of foundational neural network concepts.
- Intro to Neural Networks
- This introduction to neural networks explains how algorithms inspired by the human brain operate and puts to use those concepts when designing a neural network to solve particular problems.
- Training Neural Networks
- Learn how to train neural networks and avoid overfitting or underfitting by employing techniques like Early Stopping, Regularization, Dropout, Local Minima, and Random Restart!
- Developing a Handwritten Digits Classifier with PyTorch
- In this project, you will use your skills in designing and training neural networks to classify handwritten digits using the well-known MNIST dataset.
Taught by
Erick Galinkin
