Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 9 of 9
Full-Text Articles in Entire DC Network
Hardware Accelerators And Their Use In Computer Vision, Cameron Villone
Hardware Accelerators And Their Use In Computer Vision, Cameron Villone
Theses
The evolution of technology is impressive. Before digital, there was analog; before software, there needed hardware. This evolution is natural as we try and optimize technology for our needs. The shift to digital was fueled by the space saved from using digital systems compared to analog. When it came to software, the ability to use generic hardware in the forms of cen- tral processing units; CPUs, Graphics Processing Units; GPUs, and Random Access Memory; RAM allowed for complex software solutions to be able to run on many different devices with- out much need for translations. With software development getting so …
Towards Efficient Lifelong Machine Learning In Deep Neural Networks, Tyler L. Hayes
Towards Efficient Lifelong Machine Learning In Deep Neural Networks, Tyler L. Hayes
Theses
Humans continually learn and adapt to new knowledge and environments throughout their lifetimes. Rarely does learning new information cause humans to catastrophically forget previous knowledge. While deep neural networks (DNNs) now rival human performance on several supervised machine perception tasks, when updated on changing data distributions, they catastrophically forget previous knowledge. Enabling DNNs to learn new information over time opens the door for new applications such as self-driving cars that adapt to seasonal changes or smartphones that adapt to changing user preferences. In this dissertation, we propose new methods and experimental paradigms for efficiently training continual DNNs without forgetting. We …
Reducing Catastrophic Forgetting In Self-Organizing Maps, Hitesh Ulhas Mangala Vaidya
Reducing Catastrophic Forgetting In Self-Organizing Maps, Hitesh Ulhas Mangala Vaidya
Theses
An agent that is capable of continual or lifelong learning is able to continuously learn from potentially infinite streams of pattern sensory data. One major historic difficulty in building agents capable of such learning is that neural systems struggle to retain previously-acquired knowledge when learning from new data samples. This problem is known as catastrophic forgetting and remains an unsolved problem in the domain of machine learning to this day. To overcome catastrophic forgetting, different approaches have been proposed. One major line of thought advocates the use of memory buffers to store data where the stored data is then used …
Forensics Writer Identification Using Text Mining And Machine Learning, Saif Ali Alawar
Forensics Writer Identification Using Text Mining And Machine Learning, Saif Ali Alawar
Theses
Constant technological growth has resulted in the danger and seriousness of cyber-attacks, which has recently unmistakably developed in various institutions that have complex Information Technology (IT) infrastructure. For instance, for the last three (3) years, the most horrendous instances of cybercrimes were perceived globally with enormous information breaks, fake news spreading, cyberbullying, crypto-jacking, and cloud computing services. To this end, various agencies improvised techniques to curb this vice and bring perpetrators, both real and perceived, to book in relation to such serious cybersecurity issues. Consequently, Forensic Writer Identification was introduced as one of the most effective remedies to the concerned …
Machine Learning Classification Of Inundation Following Hurricane Florence (2018) Via L-Band Synthetic Aperture Radar And Ancillary Datasets, Alexander Melancon
Machine Learning Classification Of Inundation Following Hurricane Florence (2018) Via L-Band Synthetic Aperture Radar And Ancillary Datasets, Alexander Melancon
Theses
During and after flooding events, mapping the extent of floodwaters aids in the distribution of resources, recovery efforts, and damage assessment practices. Development of a land cover classification system focused on mapping inundation after major hurricane events using synthetic aperture radar (SAR) data could allow for the production of near-real-time inundation mapping, enabling government and emergency response entities to get a preliminary idea of a developing situation. In response to Hurricane Florence of 2018, NASA JPL collected numerous swaths of quad-pol L-band SAR data with the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) instrument observing the record-setting river stages across …
Reducing Body Contact Using Smart Mobile App And Machine Learning Soltutions, Rashed Saeed Abdulrahman Shaliya
Reducing Body Contact Using Smart Mobile App And Machine Learning Soltutions, Rashed Saeed Abdulrahman Shaliya
Theses
The physical contact or the daily body interaction with people by shaking hands, using electronic and payment cards or touching objects such as devices, pens, access cards and gates, all these habits increase the proportion of spreading microbes, viruses and spread diseases among the people all over the world. This project illustrates how body contact can lead to a global disaster by spreading dangerous diseases and deadly viruses among people because of their daily dealings and routine. Analytical techniques were used to explore the relevant data and visualize how body contact increases the infection of a disease to become a …
High-Capacity Directional Graph Networks, Miguel Dominguez
High-Capacity Directional Graph Networks, Miguel Dominguez
Theses
Deep Neural Networks (DNN) have proven themselves to be a useful tool in many computer vision problems. One of the most popular forms of the DNN is the Convolutional Neural Network (CNN). The CNN effectively learns features on images by learning a weighted sum of local neighborhoods of pixels, creating filtered versions of the image. Point cloud analysis seems like it would benefit from this useful model. However, point clouds are much less structured than images. Many analogues to CNNs for point clouds have been proposed in the literature, but they are often much more constrained networks than the typical …
Machine Learning-Enabled Resource Allocation For Underlay Cognitive Radio Networks, Fatemeh Shah Mohammadi
Machine Learning-Enabled Resource Allocation For Underlay Cognitive Radio Networks, Fatemeh Shah Mohammadi
Theses
Due to the rapid growth of new wireless communication services and applications, much attention has been directed to frequency spectrum resources and the way they are regulated. Considering that the radio spectrum is a natural limited resource, supporting the ever increasing demands for higher capacity and higher data rates for diverse sets of users, services and applications is a challenging task which requires innovative technologies capable of providing new ways of efficiently exploiting the available radio spectrum. Consequently, dynamic spectrum access (DSA) has been proposed as a replacement for static spectrum allocation policies. The DSA is implemented in three modes …
An Artificial Neural Networks Based Temperature Prediction Framework For Network-On-Chip Based Multicore Platform, Sandeep Aswath Narayana
An Artificial Neural Networks Based Temperature Prediction Framework For Network-On-Chip Based Multicore Platform, Sandeep Aswath Narayana
Theses
Continuous improvement in silicon process technologies has made possible the integration of hundreds of cores on a single chip. However, power and heat have become dominant constraints in designing these massive multicore chips causing issues with reliability, timing variations and reduced lifetime of the chips. Dynamic Thermal Management (DTM) is a solution to avoid high temperatures on the die. Typical DTM schemes only address core level thermal issues. However, the Network-on-chip (NoC) paradigm, which has emerged as an enabling methodology for integrating hundreds to thousands of cores on the same die can contribute significantly to the thermal issues. Moreover, the …