Abstract

In this training, we will see some Deep Learning concepts with Keras. The goal is to provide all the tools and knowledge to make the audience able to start their own Deep Learning projects. We will examine a real image recognition project and use it to show the process to develop the model from start to end.

We will start examining the business needs and designing the solution. We will explain how to create a multi layer network and then we will go through more sophisticated topics such as implementing different types of networks (for example Convolutional Neural Network) for Image Recognition, using dropouts and random noise to improve results, select the proper architecture and use pre-trained models.

We will also address some more advanced topics necessary to go behind internet tutorials.

Agenda
Hands-on: Setting up environment and tools 45min
Theory: Terminology and related techniques. Recap of basic topics related to the course; Basic concepts like perceptron, neural layers CNN 45 min
Hands-on: Code session to gain practical experience on perceptron and CNN 2h
Theory: Different types of networks and their use cases 45 min
Hands-on: Exploring more advanced topics: 45 min
Theory: Other neural network architecture 45min 

Course objectives
In this training, we will see some Deep Learning concepts with Keras. The goal is to provide all the tools and knowledge to make the audience able to start their own Deep Learning projects. We will examine a real image recognition project and use it to show the process to develop the model from start to end.
We will start examining the business needs and designing the solution. We will explain how to create a multi layer network and then we will go through more sophisticated topics such as implementing different types of networks (for example Convolutional Neural Network) for Image Recognition, using dropouts and random noise to improve results, select the proper architecture and use pre-trained models.
We will also address some of the challenge of implementing it in production. 

Target audience
Workshop is intended for Data Scientists, Analysts and Developers that plans to start their first deep learning project, to save them time and resources and provide all the basic informations to get started straight away. 

Technical Prerequisites
Attendants should have a laptop and Python installed with pip available. They should also download this images will be used as a data set for the workshop.