Deep neural networks have been successfully applied to forward predicting optical
response and inverse designing topological structure of nanophotonic devices. However …

This thesis focuses on developing machine learning methods for autonomous classification
and decision making, especially on two case studies: traffic speed prediction and cancer …

Signal representation and processing are the backbone of mathematically-aided
engineering. Among the myriad of ideas and results in that realm, many sorts of algorithms …

The squash function in capsule networks (CapsNets) dynamic routing is less capable of
performing discrimination of non-informative capsules which leads to abnormal activation …

Automating the classification of images is difficult in specialized areas because often there is
insufficient labeled data to train a convolutional neural network, the most popular model for …

This thesis is a study of the 2D, closed, and planar contour classification using deep learning
(DL). In this context, two main topics are treated: the certification and the explainability of …

Malaria is a female Anopheles mosquito-borne disease that transmits a motile infective form
to the host body such as humans, which reproduce asexually in the blood cells of the host. It …

Abstract While Capsule Networks overcome many shortcomings of Convolutional Neural
Networks by taking spatial hierarchies between features into consideration and providing a …

Abstract Capsule Neural Networks (CapsNet) serve as an attempt to model the neural
organization in biological neural networks. Through the routing-by-agreement algorithm, the …

Convolutional neural networks (CNNs) have been widely used in the computer vision
community, significantly improving the state-of-the-art. But learning good features often is …