Deep learning EE-559
This course explores how to design reliable discriminative and generative neural networks, the ethics of data acquisition and model deployment, as well as modern multi-modal models.
The course equips students with a comprehensive foundation of deep learning, enabling students to design and train neural networks for a wide range of tasks. Topics include:
- Deep learning applications (natural language processing, computer vision, audio processing, biology, robotics, science), principles and regulations
- Loss functions, data and labels, data provenance
- Training models: gradients and initialization
- Generalization and performance
- Transformers
- Graph neural networks
- Multi-modal models
- Generative adversarial networks
- Variational autoencoders
- Diffusion models
- Interpretability, explanations, bias and fairness
Group mini-project
The group mini-project for EE-559 aims to support a safer online environment by tackling harmful content in various forms, ranging from text and images to memes, videos, and audio content.
The objective is to develop deep learning models that help foster healthier online interactions by automatically identifying hate speech across diverse content formats.
These deep learning models shall be carefully designed to prioritize accuracy and context comprehension, ensuring they differentiate between harmful hate speech and legitimate critical discourse or satire.
At the end of each semester, students present their work on deep learning to foster safer online spaces in an open poster sessions. The next session will take place on 27 May 2026.
Student projects
Student projects supervised during the AY 2025/2026:
- Conversational data exploration
- LLM-based document analysis
- VLM-based recognition and interpretation
- VLM for workflow automation
- Forecasting disruptive technologies
- Data integration and visualization
- Identifying emerging technologies
- Autonomous system self-localisation
- Instrumental solo detection in live music
- Audiovisual archives annotation
- Swiss legal agent
- Red teaming for LLM safety enhancement
- Adversarial neuro-silencing