About this Event
Summary
This workshop is aimed at programmers that wish to incorporate neural network approaches in their projects but are not sure where to start. At the end of the workshop the attendee should have a working understanding of the PyTorch library and should be able to apply his or her knowledge to new machine learning tasks. Basic programming skills in Python are recommended as is a rudimentary understanding of calculus.
Syllabus
- What is PyTorch and what problem does it solve?
- How does the autograd method work and how does it help us?
- Basics of neural networks: linear layers, convolutions, activation functions
- Making a model: data preparation, model definition, training and evaluation
- Hands on: Create a neural network model on real data for the task of classification
Instructor
Peter Mlakar is a PhD student at the Faculty of Computer and Information Science, University of Ljubljana, where he also received his master’s degree in Computer Science. Currently employed at the Slovenian Environment Agency, he is working on improving medium-range weather forecasts using machine learning, with special emphasis on deep learning and probabilistic approaches.
Attendee equipment prerequisites
It is recommended that the participants bring a laptop with: access to Google Colab or a working Python installation including PyTorch, Torchvision, and Torchaudio (version 2.1).
Event Venue & Nearby Stays
Faculty of Computer and Information Science, 113 Večna pot, Ljubljana, Slovenia
USD 0.00