About the workshop
The workshop will provide an overview of key machine learning concepts, from supervised learning to deep neural networks, and will introduce popular architectures such as Convolutional Neural Networks (CNNs) and transformers. Participants will have the opportunity to apply these models using Python to real-world data.
Deep learning is a subset of machine learning that powers many recent advances in artificial intelligence, allowing computers to analyze complex data such as text and images with remarkable accuracy. This course will serve as an introduction to deep learning with Python, specifically tailored for social science research.
The instructor will be Reto Wüest, PhD, an experienced political scientist, researcher, and lecturer in quantitative methods.
Program
The workshop serves as an introduction to deep learning with Python, tailored for social scientists.
Topics include:
Day 1 (Morning):
- Introduction to Machine Learning and supervised learning
- Shallow and deep neural networks
- Understanding loss functions
Lunch at 12 o’clock
Day 1 (Afternoon):
- Fitting models and measuring performance
- Introduction to Python
Day 2 (Morning):
- Convolutional Neural Networks (CNNs)
- Practical session on CNNs with Python
Lunch at 12 o’clock
Day 2 (Afternoon):
- Transformers
- Practical session on Transformers with Python
This schedule offers hands-on practice and foundational knowledge to help you apply deep learning techniques in research.
The deadline for signing up for this workshop has passed. Please contact Nikolai Czajkowski or Stina Petersen if you have questions regarding this workshop.