Deep Learning Part 1: 2019 Edition (v3)

Course Materials

• Application Announcement: closed

• Website (officially released in early 2019)

  The 3rd edition of course.fast.ai - coming in 2019. This 7-week course is designed for anyone with at least a year of coding experience, and some memory of high-school math. The course is taught in Python, using the fastai library and PyTorch. You will start with step one—learning how to get a GPU server online suitable for deep learning—and go all the way through to creating state of the art, highly practical, models for computer vision, natural language processing, and recommendation systems.

• Forum (suitable for people who have not studied deep learning before)

• Forum for advanced questions

• FAQ, resources, and official course updates

• Jupyter Notebook and Code

Lessons Cover

Many topics, including:

• image recognition

  • multi-label image classification

  • different kind of images

• Convolutional Neural Networks (CNNs)

  • image segmentation with U-Net

• overfitting

• embeddings

  • collaborative filtering: recommendation systems

• Natural Language Processing (NLP)

  • language model, sentiment analysis

  • text classification

• Recurrent Neural Networks (RNNs)

  • RNN architecture from scratch

• tabular/structured data

  • time-series prediction using neural network

• CNN architecture

  • back to computer vision

  • CNN in-depth and ResNets from scratch