Deep Learning on the Edge
Advanced-level lab-based course. Build and experiment with deep-learning models implemented on low-power GPU edge computing device. Topics: architectures of low-power GPU devices, algorithms and DL models suitable for edge implementation, CUDA language, pre-processing of data, labeling for ground-truth annotation, profiling techniques, connectivity between edge devices and cloud computing servers, real-life data for experimentation, comparison of performance for a variety of methods, comparison of performance of edge-computing and cloud computing approaches.
Topics
- architectures of low-power GPU devices
- algorithms and DL models suitable for edge implementation
- CUDA language
- pre-processing of data
- labeling for ground-truth annotation
- profiling techniques
- connectivity between edge devices and cloud computing servers
- real-life data for experimentation
- comparison of performance for a variety of methods
- comparison of performance of edge-computing and cloud computing approaches
Topics explicitly listed in official catalogue description
Prerequisites & course information
Prerequisites: Machine Learning, Linear Algebra, Probability and statistics, EECS E4040 Neural Networks and Deep Learning (or similar) E4620 - Numerical Methods for Data Science (or similar) Working knowledge of Python and a DL SW framework such as TensorFlow or PyTorch
Sources
- Course catalogue ↗2026-2027