This course spans 7 weeks and focuses on deep learning neural networks. It follows a practical top down approach for programmers with 1 year experience.
- Set up your own GPU server in the cloud
- Use the fastai and Pytorch libraries in python to train and run deep learning models
- Build, debug, and visualize a state of the art convolutional neural network (CNN) for recognizing images
- Build state of the art recommendation systems using neural-network based collaborative filtering
- Build state of the art time series and structured data models using categorical embeddings
- Get great results even from small datasets, by using transfer learning
- Understand the components of a neural network, including activation functions, dense and convolutional layers, and optimizers
- Build, debug, and visualize a recurrent neural network (RNN) for natural language processing (NLP), including developing a sentiment classifier which beat all previous academic benchmarks.
- Recognize and deal with over-fitting, by using data augmentation, dropout, batch normalization, and similar techniques