Chrysolites Tech Academy

Video by freeCodeCamp.org · taught by Kylie Ying · streamed from YouTube. All rights remain with the creator.

Lesson 4: Text Classification with TensorFlow

About this lesson

This course by Kylie Ying teaches how to classify text with neural networks in Python and TensorFlow, working in Google Colab notebooks so that you can follow along in the browser without installing anything. It begins by setting up a notebook and importing a dataset of wine reviews that will be used for the final project. The course then steps back to explain what machine learning is and how its parts fit together. It covers features, the inputs a model learns from, and outputs, the predictions it makes, and describes the anatomy of a dataset, including how data is divided into training, validation and test sets. A section on assessing performance explains how loss functions and accuracy measure how well a model is doing. With those foundations in place, the course introduces neural networks and then TensorFlow, the library used to build them. The first hands-on project builds a feedforward neural network on a tabular dataset of numerical measurements, covering the preparation of the data, the design of the network and its training and evaluation. The course next explains recurrent neural networks, which process sequences such as text one step at a time while keeping a memory of what came before. The final project returns to the wine reviews and builds text classification networks for them, first using a pre-trained text embedding and then a model with a recurrent layer, and compares the results. Afterwards, read Chapter 4 of the course book, which works the loss functions 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.