Chrysolites Tech Academy
AI

Deep Learning with TensorFlow and Keras

Build neural networks with TensorFlow 2 and Keras: tensors, dense and convolutional networks, transfer learning, text classification and Q-learning.

Intermediate · 4 video lessons · 4-chapter course book · Free

Start learning Open course book

About this course

TensorFlow is one of the most widely used libraries for deep learning, and its built-in Keras interface lets you describe a network in a few lines of Python, train it and use it for predictions. Knowing how to load and shape data, choose layers and losses, read training curves and reuse pre-trained models is the practical core of building neural networks.

This course follows four freeCodeCamp courses. A complete seven-hour course covers TensorFlow from tensors through core algorithms, neural networks, computer vision, language and reinforcement learning. A shorter crash course builds image and text classifiers step by step. A Keras course covers data processing, convolutional networks, fine-tuning and data augmentation, and a final lesson classifies text with feedforward and recurrent networks. Each lesson comes with an original book chapter of worked examples.

What you will learn

  • Create, reshape and reason about tensors of any rank
  • Build, compile, train and evaluate Keras models for images and text
  • Count a model's parameters and predict layer output shapes by hand
  • Use convolutional networks, data augmentation and transfer learning
  • Prepare text with tokenisation and embeddings for classification

Who this course is for

Python programmers who know the basics of machine learning and want to build neural networks. Earlier courses on this site, such as Machine Learning Fundamentals and How Neural Networks Work, are good preparation.

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.