Abstract: In this workshop, we will see some Deep Leaning concepts with Keras. 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 and how to overcome the engineering complications in a self hosted server. Then we will go through how to re-train the model and evaluate the results.
Bio: Leonardo De Marchi holds a Master in Artificial intelligence and has worked as a Data Scientist in the sport world, with clients such as New York Knicks and Manchester United, and with large social networks, like Justgiving. He now works as Lead Data Scientist in Badoo, the largest dating site with over 340 million users.