Deep Learning Made Easy with Keras: Text, image and time-series analysis

Let's get practical!

Join us in this two-hour coding and learning session by Nikolaos Passalis that will take place on Tuesday 20/02 - 19:00, at OK!Thess.

Keras is a well known deep learning library for Python that significantly simplifies the process of developing and training deep learning models. Keras provides support for all the major deep learning paradigms, ranging for simple Multilayer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) to Recurrent Neural Networks (RNNs) and Generative Adversarial Networks (GANs).

First, the architecture and the capabilities of the Keras library will be presented. Then, we will go through several examples demonstrating how Keras can be used to apply several deep learning models (MLPs, CNNs, RNNs, word embeddings, etc) to a wide range of domains and applications (image classification and representation, topic classification from textual documents, sentiment analysis, time series classification, and others).

Nikolaos Passalis is a Ph.D. candidate and researcher in the Department of Informatics, Aristotle University of Thessaloniki. He obtained his B.Sc. in Informatics in 2013 and his M.Sc. in Information Systems in 2015 from Aristotle University of Thessaloniki, Greece. His research interests include deep learning, computational intelligence and information retrieval. His doctoral studies are supported by the General Secretariat for Research and Technology (GSRT) and the Hellenic Foundation for Research and Innovation (HFRI).

• What to bring
Participants are encouraged to bring their laptops with the Keras library installed (https://keras.io/#installation) to actively participate in the session.