HANDS-ON Introduction to Deep Learning: Techniques and Best Practices
Please note: the instructor will be presenting from an offsite location and will not be present in the classroom.
Instructors: Ahmed Mohammed and Asbjørn Berge, SINTEF Digital, and Marius Pedersen, Norwegian University of Science and Technology
Level: Introductory
Duration: 2 hours
Course Time: 15:45 - 17:45
Prerequisites: Familiarity with Python programming. Students are required to bring a laptop with Colab loaded and set up prior to the course. To use Colab you will need a Google account. Students should familiarize themselves with the following Source Code References:
Benefits
This course enables the attendee to:
- Build a foundation in deep learning that can be applied to a wide range of fields, including computer vision, natural language processing, and robotics.
- Gain knowledge of best practices for handling color data in deep learning to improve model performance and accuracy.
- Understand how to pre-process color images for deep learning tasks.
Course Description
This course is a concise and focused on hands-on introduction to deep learning with PyTorch, covering the basics of pre-processing color images and applying convolutional neural networks (CNNs) for color image classification. The course is organized as 25% theory and 75% practical. It covers topics such as transfer learning for color image analysis, and the effects of texture, color, and shape biases in deep learning. Best practices for handling color data in deep learning are also discussed. The course includes six modules, each ranging from 10 to 30 minutes in length, that provide an overview of the key concepts and techniques used in modern deep learning applications.
Intended Audience: individuals interested in a hands-on experience with deep learning, particularly with a focus on color image analysis. This could include students, researchers, and professionals in fields such as computer science, engineering, and data science.
Ahmed Mohammed received his master’s degree in electronics and information engineering from Chonbuk National University in South Korea and his PhD in computer science from the Norwegian University of Science and Technology (NTNU). He is currently a research scientist at SINTEF Digital and an adjunct associate professor with NTNU. His research interests include machine learning and computer vision, with emphasis on medical imaging and 3D vision for explainable and data-efficient learning.
Marius Pedersen has a bachelor’s degree in engineering data and master’s degree in technology and media engineering from Gjøvik University College. He received his PhD in color image technology from the University of Oslo. Pedersen is professor in the Department of Computer Technology and Informatics at NTNU, where he is also head of the Colorlab. His work is aimed at quality assessment of images with classical and deep learning approaches.
Asbjørn Berge’s main interest is in computer vision and drone technology.