CS231n: Convolutional Neural Networks for Visual Recognition
CS231n is a excellent free online course offered by Stanford.
In-Depth Course Material
This course features in-depth course material about visual recognition tasks such as image classification, localization and detection. It offers a deep dive into details of the deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification.
Hands On Assignments
There are three assignments. Students implement, train and debug their own neural networks and gain a detailed understanding of all the processes involved, including:
- Learning Algorithms
- Backpropagation
- Fine-Tuning
The assignments are built around iPython Notebook, which is an interactive notebook environment similar to Maple. I personally think this is an excellent choice.