- This event has passed.
Fundamentals of Deep Learning for Computer Vision
June 27, 2018 @ 9:00 am - 5:30 pm CEST
In this hands-on course, you will learn the basics of deep learning by training and deploying neural networks.
Beginners will learn what deep learning is and discover how easy it is to get started.
Experienced developers or data scientists will learn to use and appreciate DIGIT, which is a free and interactive tool for easy prototyping, training and deployment of deep neural networks.
You will learn how to:
- Implement common deep learning workflows, such as image classification and object detection.
- Experiment with data, training parameters, network structure and other strategies to increase performance and capability.
- Deploy your neural networks to start solving real-world problems.
After completing the course, you will receive a certificate from NVIDIA DLI.
Instructor
Henrik Pedersen (PhD) is a Senior Computer Vision Engineer at the Alexandra Institute. Over his career, Henrik has been in various academic positions, covering research and teaching in computer vision and deep learning. His interests lie in exploring deep learning techniques for object detection and recognition using photorealistic, synthetic images for training. Henrik is an experienced educator and has played a key role in building up the vibrant deep learning community at the Alexandra Institute.
Agenda
| 9:00 | Deep Learning Demystified and Applied Deep Learning (lecture) |
| 9:45 | Break |
| 10:00 | Image Classification with DIGITS (lab*) |
| 12:00 | Lunch |
| 13:00 | Object Detection with DIGITS (lab*) |
| 15:00 | Break |
| 15:15 | Neural Network Deployment with DIGITS and TensorRT (lab*) |
| 17:15 | Q&A and closing comments |
* Please note that attendees MUST bring their own laptops.
Prerequisites: Programming skills (C/C++, Python or similar)
Duration: 8 hours
Framework: Caffe, NVIDIA DIGITS™
Language: English
If you have any questions, please send an e-mail to henrik.pedersen@alexandra.dk.
Free of charge. To reserve your seat, you MUST register with a valid university e-mail address. So you must be either a student or employed at a university to attend.