Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Engineering
Mathematical Optimization Algorithms For Model Compression And Adversarial Learning In Deep Neural Networks, Tianyun Zhang
Mathematical Optimization Algorithms For Model Compression And Adversarial Learning In Deep Neural Networks, Tianyun Zhang
Dissertations - ALL
Large-scale deep neural networks (DNNs) have made breakthroughs in a variety of tasks, such as image recognition, speech recognition and self-driving cars. However, their large model size and computational requirements add a significant burden to state-of-the-art computing systems. Weight pruning is an effective approach to reduce the model size and computational requirements of DNNs. However, prior works in this area are mainly heuristic methods. As a result, the performance of a DNN cannot maintain for a high weight pruning ratio. To mitigate this limitation, we propose a systematic weight pruning framework for DNNs based on mathematical optimization. We first formulate …
Augmented Human Machine Intelligence For Distributed Inference, Baocheng Geng
Augmented Human Machine Intelligence For Distributed Inference, Baocheng Geng
Dissertations - ALL
With the advent of the internet of things (IoT) era and the extensive deployment of smart devices and wireless sensor networks (WSNs), interactions of humans and machine data are everywhere. In numerous applications, humans are essential parts in the decision making process, where they may either serve as information sources or act as the final decision makers. For various tasks including detection and classification of targets, detection of outliers, generation of surveillance patterns and interactions between entities, seamless integration of the human and the machine expertise is required where they simultaneously work within the same modeling environment to understand and …
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Dissertations - ALL
Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Experience-Driven Control For Networking And Computing, Zhiyuan Xu
Dissertations - ALL
Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …