Georgios Deligiorgis

My name is Georgios Deligiorgis and I'm a Machine Learning Engineer working at H&M Group. I'm part of the AI Exploration and Research Team focusing on enabling new use-cases, implement and evaluate Proof of Concepts and research, investigate and improve new models. I'm currently attending in parallel my second MSc in Decision Analysis and Data Science from Stockholm University. I already have obtained an MSc in Machine Learning from the Royal Institute of Technology (KTH) and a BSc in Physics from the University of Crete (UOC). The field of my interest is Deep Learning and how to use it to solve complex and difficult problems.


Zero To Hero Tutorial on a Deep Learning Classification Task
Georgios Deligiorgis, Marco Trincavelli, David Andersson

Live Stream:

This workshop will demonstrate a zero-to-hero tutorial on how to solve a classification task using deep learning. The tutorial kicks off demonstrating a simple classification task on synthetic data, first in low and then in high dimension. Then, a harder classification task based on FashinMNIST, a famous dataset containing images of clothes, will be tackled. Apart from solving the classification task itself, we will show how to generate and analyze embedding vectors that can be used to solve other downstream tasks, different from the original classification problem on which the model was trained. Finally, we are going to face a more advanced type of classification problem, namely, predicting links on a graph using Graph Neural Networks. Link prediction will be demonstrated on an open source dataset that contains information about collaborations among authors of scientific papers. The target of this workshop is to show how we can use Python to solve the the aforementioned tasks, taking into account both the data science aspects and the engineering and project lifecycle related ones. In particular, the python packages that we are going to cover in the workshop are PyTorch, PyTorch-Lightning, Deep Graph Library.

Data Science, AI, and Machine Learning