This page was translated by an AI (LLM) with a cursory human check and is awaiting full review.
Practical Introduction to Deep Learning (IPDL)
Manager : Kamel Guerda
Instructors : Members of the IDRIS support team
This training aims to provide participants with fundamental knowledge in deep learning, emphasising the understanding of basic concepts and essential best practices. It aims to equip participants with the essential skills needed to start in the field of deep learning, thus preparing participants to explore more advanced techniques and architectures in the future. For this, you can also register for the ArchDL training, which explores various architectures. The ArchDL training is systematically given following IPDL.
- Target audience
- Prerequisites
- Duration and practical info
- Course content
- Course materials
- Upcoming sessions
Target audience
This training is ideal for complete beginners in Artificial Intelligence (AI) provided they have the prerequisites. It is aimed at a wide range of profiles, including engineers, researchers, developers, technicians, PhD students, project managers, among others, who wish to familiarise themselves with the fundamental principles of Deep Learning.
Prerequisites
Although the training is introductory, a basic understanding of algebra and statistics is required.
Regarding programming, a minimal knowledge of Python, particularly its syntax, is necessary but sufficient to participate effectively in the practical sessions.
Duration and practical info
This training lasts 2 days. Welcome is from 09:00 with classes starting at 9:30. Supervision is provided until 18:00 with an average finish at 17:30 (varying by group depending on practicals).
It takes place exclusively in-person at the premises ofIDRIS in Orsay (91).
Attendance
Minimum : 10 people ;
Maximum : 18 people.
Course content
This training approaches deep learning in a pragmatic way, defining its place in the artificial intelligence ecosystem and explaining the key concepts related to models, their training and the exploitation of results.
The practical exercises, combining the use of intuitive graphical interfaces and Python notebooks with PyTorch, will allow an effective integration of methodological concepts, thus fostering the development of an informed deep learning practice.
Plan :
1. Neural Networks:
- Context, definitions and history
- Fundamentals of deep learning
- Graphical practical application
- PyTorch
- Practical application
2. Methodology:
- Data management
- Training and evaluating a model
- Practical application
For an efficient execution of the practical parts, these will take place on the Jean Zay supercomputer. A workstation with access to the IDRIS supercomputer is provided to the learners. Experience in using a supercomputer, as well as prior access to it, are not required.
Course materials
All course materials, including slides, notes, and practical exercises, are provided under the following license: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0). For more details on the license, please consult this page.
To view the dates of the upcoming sessions for this training, go to the following page:
Registration
CNRS/French university staff | External participants |
Are you a member of CNRS or a French university staff? Your registration is free via our server. | Our training is aimed at all professionals from companies, public bodies and individuals. |
If you wish to deepen your discovery of deep learning, we invite you to consult the ArchDL training which explores various neural network architectures.