Chrysolites Tech Academy

Video by freeCodeCamp.org · taught by Jeremy Howard and Sylvain Gugger · streamed from YouTube. All rights remain with the creator.

Lesson 1: Practical Deep Learning for Coders

About this lesson

This course from fast.ai, developed by Jeremy Howard and Sylvain Gugger, is a complete introduction to deep learning designed to be accessible to anyone with about a year of coding experience, preferably in Python, and secondary-school mathematics. It teaches from the top down, so that you train useful models from the start and learn the theory as you need it. This video contains the first six lessons; the course's last two lessons, on tabular data and natural language processing, are published as a second video. The first lesson trains your first models, showing how a pre-trained network can be fine-tuned to classify images and introducing the vocabulary of deep learning. The second lesson discusses how to weigh evidence, including what p-values do and do not tell you. The third lesson covers production and deployment, from gathering and cleaning an image dataset to turning a trained model into an application that others can use. The fourth lesson opens the black box by building stochastic gradient descent from scratch on images of handwritten digits, explaining losses, gradients, mini-batches and simple neural networks along the way. The fifth lesson is devoted to data ethics, examining the ways machine learning systems can cause harm and how practitioners can prevent it. The sixth covers collaborative filtering, the technique behind recommendation systems. Afterwards, read Chapter 1 of the course book, which works a p-value by hand.

Install Chrysolites Tech Academy

Android / Chrome / Edge: open the browser menu and choose Install app or Add to Home screen.

iPhone / iPad (Safari): tap the Share button, then Add to Home Screen.