This introductory course on deep learning offers a deep dive into advanced neural network architectures and their
applications to the Social Sciences.
Topics
This course offers a deep dive into advanced neural network architectures and their applications, including:
- Introduction to the use of deep learning techniques in social sciences
- Basic Machine Learning concepts: regression, classification, and models
- Neural Networks: Perceptrons, Multi-Layer Perceptrons, XOR problem, activation functions, backpropagation, and gradient descent
- Convolutional Neural Networks: Image processing implementations in PyTorch
- Graph Neural Networks and their Python implementations
- Recurrent Neural Networks and Long Short Term Memory networks for time series analysis
- Generative deep learning techniques
- Advanced topics: Diffusion Models, Reinforcement Learning, and Large Language Models based on transformer architectures like the GPT series in NLP with practical implementations in PyTorch
Format
The course is structured as:
- 13 lectures on the theory of Deep Learning
- 8 coding labs
- 3 guest researchers seminars
- 1 students presentation day
Grading
The course grade is composed of four assignments delivered during the semester (40%) and a final project (60%).
Assignments
You will have 3 weeks to work individually on each assignment. The assignments will be delivered on the following dates:
- April 24 - Multilayer Perceptron
- May 15 - Convolutional Neural Network
- June 5 - Graph Neural Networks/Recurrent Neural Networks
- June 21 - Large Language Models
Exercises
A practical part of coding exercises connected to the lectures will be offered. The exercises will not be graded.
Theory Seminars
April 16, 2025 - Shallow Neural Networks
April 23, 2025 - The Multilayer Perceptron
April 30, 2025 - Regularization of Neural Networks
May 7, 2025 - Convolutional Neural Networks
May 14, 2025 - Graph Neural Networks
May 21, 2025 - Recurrent Neural Networks
May 28, 2025 - Natural Language Processing
June 4, 2025 - Transformer and Attention
June 25, 2025 - Large Language Models
July 2, 2025 - Reinforcement Learning and Alignment
July 9, 2025 - Image Generation and Multimodality
Labs and Coding Sessions
April 17, 2025 - Lab: GPU Server + Machine Learning Basics
April 24, 2025 - Lab: Building a MLP with PyTorch
May 8, 2025 - Lab: Building a CNN to classify clothes
May 15, 2025 - Lab: Introduction to PyTorch Geometric
May 22, 2025 - Lab: Time Series + Guest Research Seminar
June 5, 2025 - Lab: Working with embeddings
June 26, 2025 - Lab: Fine-tuning LLMs
July 10, 2025 - Lab: VAE and Diffusion Models
Seminars and Presentations
May 22, 2025 - A. Bellina (Sony CSL) "Conformity in Humans and LLMs" (D301-13:30)
July 3, 2025 - E. Francazi (EPFL) "Emergence of bias in deep neural networks predictions"
July 16, 2025 - Students Presentation Day
July 17, 2025 - S. Petruzzi (Sapienza) "Introduction to Mechanistic Interpretability of LLMs"