Contact us     |

Using Deep Learning For Image and Sequence Analysis

Date:

Monday, 31st August

Time:

17:00 to 20:00 (CEST)

Instructors and helpers 

  • Petr Simecek | Central European Institute of Technology, Masaryk University, Czech Republic
  • Panagiotis Alexiou | Central European Institute of Technology, Masaryk University, Czech Republic

Summary

Computational Biologists have been using Machine Learning techniques based on Artificial Neural Networks for decades. New developments in the Machine Learning field over the past years have revolutionized the efficiency of Neural Networks and bring us to the era of Deep Learning. In the news, you can read about Deep Learning beating experts in Go, Chess and StarCraft, translating texts and speech between languages, turning the steering wheels of self-driving cars and even to tag kittens, Not-Hotdogs, and tumours in images. In our field, we have witnessed such systems reaching competitive accuracy with experienced radiologists, predicting folding of proteins and calling single nucleotide polymorphisms in genomic data better than any other method.

Powerful, easy-to-use python packages for Deep Learning have been developed and are freely available for use. Additionally, thanks to AWS, Microsoft Azure, Google Cloud...,  computational resources needed to train small/medium models are available with no or minimal cost. In this tutorial, we will be using fastai v2, a PyTorch-based deep learning Python library, which provides practitioners with high-level components that can quickly and easily achieve state-of-the-art results in standard deep learning domains. We will demonstrate its power on two real-world examples: classification of chest X-Ray images, and classification and generation of genomic sequences. 

We expect participants with basic or no understanding of neural networks to be able to develop and run simple Deep Learning networks by the end of this Workshop.

Target audience

This tutorial is intended for students and practitioners interested in getting their hands dirty with neural networks. It is designed to be an introduction and a starting point for further work and study. Beginners are welcome. Familiarity with Python, Jupyter Notebooks, and some experience with pandas & numpy will be useful.

Maximum participants

This tutorial is open to at most 70 attendees.

Requirements

Just a web browser and Google/GMail account (we will be using Google Collaboratory)

Schedule

Time (CEST)
Details
17:00 - 18:30 Part I: Neural Networks for Image Recognition
18:30 - 20:00 Part II: Neural Architectures for Sequential Data