The superior performance of the recent deep learning models comes at the cost of a
significant increase in computational complexity, memory use, and power consumption …

Edge devices, with their widely varying capabilities, support a diverse range of edge AI
models. This raises the question: how does an edge model differ from a high-accuracy …

People with dietary restrictions caused by certain gastrointestinal pathologies and by certain
physiological conditions need permanent monitoring of their food intake. Besides this, they …

Model pruning can enable the deployment of neural networks in environments with resource
constraints. While pruning may have a small effect on the overall performance of the model …

Model pruning is a simple and effective method for compressing neural networks. By
identifying and removing the least influential parameters of a model, pruning is able to …

This Ph. D. thesis is dedicated to enhancing the efficiency of Deep Learning by leveraging
the principle of modularity. It contains several main contributions: a literature survey on …