Deep Learning
Deep learning has significantly advanced machine perception of natural signals in recent years. This one-week course gives you hands-on experience with the newest deep learning technologies and helps you integrate them into your organisation.
Deep learning is an important tool for leading international IT companies in developing their AI strategy. Deep learning is behind many recent big advances in image classification, speech recognition, natural language processing and reinforcement learning. These developments have largely been driven by the availability of fast computers, an abundance of data and algorithmic improvements for training neural networks.
This one-week hands-on course focuses on computation and applications and will provide the participant with the foundation to apply deep learning in industry and industrial research. The courses consists of a mixture of lectures and hands-on programming exercises.
During the course, the participant will work with the following:
- The foundation for neural networks and training of neural networks.
- Well-established neural network architectures, including feed-forward neural networks, convolutional neural networks, recurrent neural networks, and transformers.
- Advanced topics such as deep generative models and reinforcement learning.
- Tricks for faster convergence in training and better performance of neural networks.
- Implementing neural networks in Python using the computation deep learning framework PyTorch for GPU acceleration and automatic differentiation.
What is in it for you?
- An operational understanding of the basics and advanced methods in deep learning.
- Hands-on experience with implementing deep neural networks in PyTorch.
- Knowledge about opportunities and pitfalls with deep learning.
- An overview of the latest the latest developments in the field.
What is in it for your company?
By having an employee who has participated in this course/programme the company has access to a person who can:
- Implement and operate well-established neural network architectures in PyTorch.
- Identify problems and tasks that are amendable to deep learning.
- Contribute to your company’s AI strategy and transform your company’s business based on deep learning.
Who is the course relevant for?
The course is aimed at all who have a professional interested in deep learning and who have basic knowledge about mathematics and programming (in particular linear algebra, basic probability theory and basic Python programming).
Practical information
Lectures:
The course consists of physical lectures and practical computer exercises. There will also be external speakers talking about their experience with operationalising deep learning in companies.
Location:
DTU Meeting Center,
Anker Engelunds Vej 1, Building 101A,
2800 Kgs. Lyngby
Denmark
Duration:
The is a one-week course that runs Monday to Friday at 09:00 – 16:30, with lectures before lunch and exercises after lunch.
Price:
20,000 DKK excl. VAT.
Cancellation:
In case of too few participants, we reserve the right to cancel or postpone the course.
Waiting list:
In case of too many participants, we reserve the right to make a waiting list.
Admission requirements
The participant should have some basic programming experience, preferably in Python, and a basic understanding of linear algebra and probability theory. Please bring your own laptop for the computer exercises.
Questions?
Contact Jes Frellsen
Associate Professor
Questions?
Contact Benjamin Mathiesen
Projekt- & kursuskoordinator
