CNS*2022 free online satellite tutorial on Keras/TensorFlow

The use of Keras with Tensor Flow applied to neural models and data analysis

C. Jarne. Universidad Nacional de Quilmes Departamento de Ciencia y Tecnología.

This tutorial will help participants implement and explore simple neural models using Keras [1] as well as the implementation of neural networks to apply Deep learning tools for data analysis. It will include an introduction to modelling and hands-on exercises. The tutorial will focus on using Keras, which is an open-source framework to develop Neural Networks for rapid prototyping and simulation with TensorFlow [2] as backend. The tutorial will show how models can be built and explored using python. The hands-on exercises will demonstrate how Keras can be used to rapidly explore the dynamics of the network. 

Keras is a framework that greatly simplifies the design and implementation of Neural Networks of many kinds (Regular classifiers, Convolutional Neural Networks, LSTM, among others). In this mini-course, we will study implementations of neural networks with Keras. It is split into two sections: On one side, we will introduce the main features of Keras, showcasing some examples, and then, we will do a set of two guided online hands-on exercises to strengthen the knowledge.

For this tutorial, you will need very basic knowledge of NumPy, SciPy, and matplotlib. To be able to carry out the tutorial, students only need to use Google Colab

 Duration 1.5–2 hours

Exercises will be available for the date of the Tutorial


[1] Francois Chollet et al. Keras., 2015.

[2] Martín Abadi, et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015.

[3] Deep Learning And Reinforcement Summer School (DLRLSS):

[4] Deep Learning with Keras. Antonio Gulli Sujit Pal. Packt Publishing Ltd. 2017.