SO Basics of Neural Networks 2025
Deep learning (DL) is a family of techniques widely used in multiple fields with excellent results. Unfortunately, DL has a steep learning curve. Fortunately, several domain-specific libraries have been developed to facilitate the use of DL models.
For the widespread adoption of these techniques, researchers should be able to design and use their own DL models. Image classification is one of the main applications of DL in astrophysics and offers a convenient way to learn about neural networks. The de facto standard to tackle this problem is Convolutional Neural Networks (CNN), a concrete deep learning architecture. This course will serve as an introduction to Deep Learning with four sessions with the following objectives: understanding the basics of neural networks, getting to know the fundamental libraries and fundamental architectures, learning how to train a CNN, gaining confidence in using CNNs for image classification tasks, and learning how to evaluate their preformance.
- Session 1: Deep Learning fundamentals
- Session 2: Convolutional Neural Networks fundamentals
- Session 3: Practical considerations in real-world CNNs
- Session 4: Evaluation
The tutor of this school is Dr Francisco Eduardo Sanchez Karhunen (Universidad de Sevilla).
There will be coffee breaks available to participants.
Contents
- Session 1: Deep Learning fundamentals
- Session 2: Convolutional Neural Networks fundamentals
- Session 3: Practical considerations in real-world CNNs
- Session 4: Evaluation
For more details, see the agenda below.
The repository with contents and materials can be found in Github (TBC)
Organizing Committee
- Rainer Schödel (Chair), IAA-CSIC, Spain
- Laura Darriba, IAA-CSIC, Spain
- Javier Moldón, IAA-CSIC, Spain