Browsing Computer Science by Title
Now showing items 752-771 of 1549
-
Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness
(University of Waterloo, 2020-08-19)Deep neural networks have been achieving state-of-the-art performance across a wide variety of applications, and due to their outstanding performance, they are being deployed in safety and security critical systems. However, ... -
Learning Automatic Question Answering from Community Data
(University of Waterloo, 2012-09-19)Although traditional search engines can retrieval thousands or millions of web links related to input keywords, users still need to manually locate answers to their information needs from multiple returned documents or ... -
Learning by Teaching: Key Challenges and Design Implications
(University of Waterloo, 2022-01-17)Benefits of learning by teaching (LbT) have been highlighted by previous studies from a pedagogical lens, as well as through computer-supported systems. However, the challenges that university students face in technology-mediated ... -
Learning Energy-Aware Transaction Scheduling in Database Systems
(University of Waterloo, 2021-09-20)Servers are typically sized to accommodate peak loads, but in practice, they remain under-utilized for much of the time. During periods of low load, there is an opportunity to save power by quickly adjusting processor ... -
Learning Factors and Determining Document-level Satisfaction In Search-as-Learning
(University of Waterloo, 2017-04-26)An important use of search engines is as a tool for learning. Search engines help users find learning material and increases their knowledge in various topics. The underlying process of learning while web searching and ... -
Learning Filters for the 2D Wavelet Transform
(IEEE, 2018)We propose a new method for learning filters for the 2D discrete wavelet transform. We extend our previous work on the 1D wavelet transform in order to process images. We show that the 2D wavelet transform can be represented ... -
Learning from Green Technology Designers
(University of Waterloo, 2014-02-13)This thesis presents results from a qualitative case study on environmentally minded technology designers, and provides an account of how these designers think, differ and behave. Through semi-structured interviews, we ... -
Learning from Partially Labeled Data: Unsupervised and Semi-supervised Learning on Graphs and Learning with Distribution Shifting
(University of Waterloo, 2007-08-20)This thesis focuses on two fundamental machine learning problems:unsupervised learning, where no label information is available, and semi-supervised learning, where a small amount of labels are given in addition to unlabeled ... -
Learning in large-scale spiking neural networks
(University of Waterloo, 2011-08-31)Learning is central to the exploration of intelligence. Psychology and machine learning provide high-level explanations of how rational agents learn. Neuroscience provides low-level descriptions of how the brain changes ... -
Learning Instruction Scheduling Heuristics from Optimal Data
(University of Waterloo, 2006)The development of modern pipelined and multiple functional unit processors has increased the available instruction level parallelism. In order to fully utilize these resources, compiler writers spend large amounts of ... -
Learning Sample-Based Monte Carlo Denoising from Noisy Training Data
(University of Waterloo, 2022-02-15)Monte Carlo rendering allows for the production of high-quality photorealistic images of 3D scenes. However, producing noise-free images can take a considerable amount of compute resources. To lessen this burden and speed ... -
Learning Sparse Orthogonal Wavelet Filters
(University of Waterloo, 2018-10-12)The wavelet transform is a well studied and understood analysis technique used in signal processing. In wavelet analysis, signals are represented by a sum of self-similar wavelet and scaling functions. Typically, the wavelet ... -
Learning to Rank in the Age of Muppets
(University of Waterloo, 2022-04-26)The emergence of BERT in 2018 has brought a huge boon to retrieval effectiveness in many tasks across various domains and led the recent research landscape of IR to transformer-related technologies. While researchers ... -
Learning Trustworthy Web Sources to Derive Correct Answers and Reduce Health Misinformation in Search
(ACM, 2022-07)When searching the web for answers to health questions, people can make incorrect decisions that have a negative effect on their lives if the search results contain misinformation. To reduce health misinformation in search ... -
Learning with non-Standard Supervision
(University of Waterloo, 2013-09-26)Machine learning has enjoyed astounding practical success in a wide range of applications in recent years-practical success that often hurries ahead of our theoretical understanding. The standard framework for ... -
Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images
(University of Waterloo, 2021-04-27)We are interested in training goal-conditioned reinforcement learning agents to reach arbitrary goals specified as images. In order to make our agent fully general, we provide the agent with only images of the environment ... -
Less is More: Restricted Representations for Better Interpretability and Generalizability
(University of Waterloo, 2023-08-22)Deep neural networks are prevalent in supervised learning for large amounts of tasks such as image classification, machine translation and even scientific discovery. Their success is often at the sacrifice of interpretability ... -
Leveraging Asymmetry and Interdependence to Enhance Social Connectedness in Cooperative Digital Games
(University of Waterloo, 2019-05-24)Play is a fundamental component of human development and is an important means of forming healthy relationships throughout life. Research has shown that the types of digital games people play, how they play them, and who ... -
Leveraging Commodity Photonics to Reduce Datacenter Network Latency
(University of Waterloo, 2014-05-22)Most datacenter network (DCN) designs focus on maximizing bisection bandwidth rather than minimizing server-to-server latency. They are, therefore, ill-suited for important latency-sensitive applications, such as high ... -
Leveraging Software-Defined Networking to Improve Distributed Transaction Processing Performance
(University of Waterloo, 2015-10-28)Recently, software-defined networking (SDN) has been transforming network technologies while NoSQL database systems are on the rise to become the de facto database systems for cloud technologies. Despite the promising ...