About Adel Bibi Adel Bibi Ph.D., Electrical and Computer Engineering Computer Vision machine learning optimization Adel Bibi is a postdoctoral research assistant in computer vision and machine learning at the Torr Vision Group working with Professor Philip Torr at the University of Oxford. Prior to that, he received his MSc and PhD degrees from King Abdullah University of Science & Technology (KAUST) where he was part of the Image and Video Understanding Lab (IVUL) advised by Professor Bernard Ghanem. Education and Early Career Adel Bibi has a Bachelor’s Degree in Electrical Engineering from Kuwait University in 2014. He received his Master Degree in Electrical Engineering from King Abdullah University of Events Presented Events Mar 29 - Apr 4, 2020 Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives Adel Bibi, Ph.D., Electrical and Computer Engineering Mar 30, 18:00 - 20:00 KAUST Computer Vision machine learning optimization In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.
Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives Adel Bibi, Ph.D., Electrical and Computer Engineering Mar 30, 18:00 - 20:00 KAUST Computer Vision machine learning optimization In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.
Engage ORCID ShareClipboard Related Sites Electrical and Computer Engineering (ECE) Image and Video Understanding Lab (IVUL) Related Content Articles 6 Events 1 Related Links Also view list of Publications on KAUST Repository Also view list of Publications on ORCID Repository Image and Video Understanding Lab