Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 121 for “"computation efficiency"”.
-
Accelerating Deep Learning by Optimising Communication and Computation Efficiency
… the computing stack. These include improving the efficiency of distributed communication across computing devices and computation on a single computing node. This thesis presents new optimisations for DNN training across multiple distributed machines and on a single machine. Our techniques reduce …
-
Spectral, Energy and Computation Efficiency in Future 5G Wireless Networks
… leverage the trade-off between the amount of computation and the energy consumed thereby. A practical communication system for wearable devices is proposed in the last part, which combines all the techniques discussed above. The challenges for wearable communication are inherent in its diverse …
-
Contributions to Structured Variable Selection Towards Enhancing Model Interpretation and Computation Efficiency
… should facilitate the model interpretation and computation efficiency. It is thus important to incorporate domain knowledge of underlying data generation mechanism to select key variables for improving the model performance. However, general variable selection techniques, such as the best subset …
-
Nanopositioning with piezoelectric actuators: Modeling, control, and applications
… with the augmented RNN model. To improve the computation efficiency of the controller, the gradient is computed analytically for the optimization problem. Nevertheless, the computation efficiency hinders the usage of large sampling frequency which is necessary for many applications. This issue …
-
Kriging assisted evolutionary computation in power system optimization
… optimization algorithms cannot satisfy both computational speed and accurate solution simultaneously. Although the traditional method is widely applied to solve the practical OPF problem due to its computation efficiency, such technique is a compromise between computation efficiency and …
-
Buildings energy data analytics with multi-task and federated learning
… year. Consequently, improving building energy efficiency is crucial for a sustainable society. Although recent studies have developed various deep-learning models for building energy load forecasting, many ignore multi-task collaborations, system reliability, and computation efficiency. …
-
Improving automatic speaker verification using front-end and back-end diversity
… verification process. In order to increase the computation efficiency, the large dimensional supervectors are replaced with speaker factors resulting in the joint factor analysis-sparse representation classification (JFA-SRC). In addition, a novel dictionary composition technique to further …
-
A Graph Convolutional Network approach for enhancing Set Covering Problem solvers
… logistics, and transportation. Solving SCP is computationally challenging due to the combinatorial explosion of potential solutions, particularly for large instances. This study proposes a Graph Convolutional Network (GCN) to approximate optimal solutions for SCP. A bipartite graph …
-
OPTIMIZATION MODELS FOR RUNWAY LOCATION, ORIENTATION AND LONGITUDINAL-GRADE DESIGN
… is used to reduce the search space and enhance computation efficiency.
-
Exact and Approximation Algorithms for the Planning and Design of Fog Networks
… a good balance between the Pareto optimality and computation efficiency. Inspired by existing evolutionary algorithms, we proposed a new evolutionary algorithm (PSONSGA). Among the three evolutionary algorithms, PSONSGA gives the best solution and it can be a valuable planning tool for real-world …
-
Dynamics analysis and applications of neural networks
… process of parameter settings and increasing computation efficiency significantly. One important focus of this thesis is on the linear threshold (LT) networks, of which the transfer functions are nonsaturating. Various dynamical properties are clarified and new theoretical results are acquired …
-
EFFICIENT AND PRIVACY-PRESERVING FEDERATED LEARNING FOR RECOMMENDER SYSTEMS
… three objectives: (i) communication and computation efficiency; (ii) privacy protection; and (iii) recommendation utility. This thesis investigates the development of efficient and privacy-preserving FedRec framework that addresses these challenges. The major contributions of this thesis …
-
Resprop : reused sparsified backpropagation
… is accompanied by a significant increase in computation and training time. In this work, we focus on accelerating training by observing that about 90% of gradients are reusable during training. Leveraging this observation, we propose a new algorithm, Reuse-Sparse-Backprop (ReSprop), as a …
-
The determination of structured Hessian matrices via automatic differentiation
… using automatic differentiation (AD) for Hessian computation, efficiency can be achieved by exploiting the sparsity existing in the derivative matrix. However, in the case where the Hessian is dense, this cannot be done and the space requirements to compute the Hessian can become very large. But …
-
Learning-based wildfire tracking with unmanned aerial vehicles
… maximum information collection. To improve the computation efficiency, a vertices-based fire line feature extraction is used to reduce the fire line targets. Simulation results under various wind conditions validate the fire prediction accuracy and UAV tracking performance.
-
Statistical inference for system and disease dynamics
… solving the equation, thus achieving enhanced computation efficiency. This thesis also discusses a methodology of monitoring the inherit change of a dynamic system, often presented through abrupt changes of key parameters, proposing an online algorithm that detects the change of key parameters …
-
DYNSYS-A Digital Computer Program for Studying the Transient Behaviour of Systems Using a Modular Approach
… Some suggestions are made for improving the computation efficiency of the program.
-
Wavefront reconstruction and mirror surface optimization for adaptive optics
… to the optimization problem is shown to improve computation efficiency.
-
Advanced mathematical optimization methods in communication networks assisted by Reconfigurable Intelligent Surfaces
… and often conflicting requirements on spectral efficiency, energy efficiency, reliability, latency, and security, which challenge the capabilities of conventional system architectures. Reconfigurable Intelligent Surfaces (RIS) have emerged as a key enabling technology that introduces …
-
Acceleration of Hardware Testing and Validation Algorithms using Graphics Processing Units
… extensively to accelerate such processes, some computational intensive applications still take long execution times. This is especially the case for testing and validation. In order tomeet the time-to-market constraints and also to come up with a bug-free design or product, the work presented in …
Page 1 of 7