2:00 pm: Thierry Dutoit - Welcome words
2:05 pm: Sidi Mahmoudi (UMons) - "Review of DNN optimization and compression methods for Edge AI systems"
During the last years, Deep Neural Networks (DNN) have gained a great importance in several research domains and applications that can learn from data. Thus, one can use DNN for image processing, actions recognition, text classification, language processing, speech recognition, etc. However, this high success of DNN models is accompanied by a high increase of computation time, architecture complexity, and memory storage. Moreover, the deployment and exploitation of DNN models in real environments is generally related to connected sensors (cameras, microphones, temperature sensors, etc.) where the inference process needs to be executed in real time on embedded or edge resources. In this work, we present an overview of the three main compression methods (pruning, quantization, knowledge distillation) that allow to reduce the computation time and memory size of DNN models while keeping a high accuracy. Experimental results are conducted within image classification, object detection and actions recognition with DNN models that were optimized and deployed on Edge AI resources such as Jetson Nano, Jetson Xavier and Jetson Orin. The obtained results showed that we could reach a compression factor of around 6x while keeping a good accuracy, and we also observe a speedup of 3x compared to non-compressed models.
Keywords: Deep Neural Networks, DNN compression, pruning, quantization, knowledge distillation, images classification, object detection, actions recognition.
3:10 pm: Louis Billot (UMons) - "The challenges of data transfer and processing on low resource hardware for AI applications"
3:20 pm: Mohamed Benkedadra & Sidi Ahmed Mahmoudi (UMons) - "Edge AI for securing railway sites"
3:45 pm: Nicolas Amand (LiEU network)- "Intellectual property rights and database protection"
4:00 pm: David Lhoir (LiEU network) - "The data management plan: concept, goals and tools"
4:15 pm: End