Browsing University of Waterloo by Subject "deep neural networks"
Now showing items 1-8 of 8
-
Deep Context Resolution
(University of Waterloo, 2018-05-17)Conversations depend on information from the context. To go beyond one-round conversation, a chatbot must resolve contextual information such as: 1) co-reference resolution, 2) ellipsis resolution, and 3) conjunctive ... -
Degraded Reference Image Quality Assessment
(University of Waterloo, 2021-12-23)Images/videos are playing a more and more important role in the 21st century. The perceived quality of visual content often degrades during the process of acquisition, storage, transmission, display and rendering. Since ... -
Domain Knowledge Guided Testing and Training of Neural Networks
(University of Waterloo, 2021-08-26)The extensive impact of Deep Neural Networks (DNNs) on various industrial applications and research areas within the last decade can not be overstated. However, they are also subject to notable limitations, namely their ... -
Image Quality Assessment: Addressing the Data Shortage and Multi-Stage Distortion Challenges
(University of Waterloo, 2020-09-25)Visual content constitutes the vast majority of the ever increasing global Internet traffic, thus highlighting the central role that it plays in our daily lives. The perceived quality of such content can be degraded due ... -
Image/Video Compression: Human and Computer Vision Perspectives
(University of Waterloo, 2020-05-15)As we start a new decade, image and video compression should further improve to satisfy each of the human and computer visions. Human and computer visions have different perspectives on the perceived images and videos, ... -
Natural Language Generation with Neural Variational Models
(University of Waterloo, 2018-08-13)Automatic generation of text is an important topic in natural language processing with applications in tasks such as machine translation and text summarization. In this thesis, we explore the use of deep neural networks ... -
Spiking Deep Neural Networks: Engineered and Biological Approaches to Object Recognition
(University of Waterloo, 2018-01-08)Modern machine learning models are beginning to rival human performance on some realistic object recognition tasks, but we still lack a full understanding of how the human brain solves this same problem. This thesis combines ... -
Studying CNN representations through activation dimensionality reduction and visualization
(University of Waterloo, 2021-10-01)The field of explainable artificial intelligence (XAI) aims to explain the decisions of DNNs. Complete DNN explanations accurately reflect the inner workings of the DNN while interpretable explanations are easy for humans ...