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 34 for “"Computational memory"”.

  1. Storage Capacity of the Linear Associator: Beginnings of a Theory of Computational Memory

    … the linear-associator, as both a memory and a classifier. Toward this end, a theory of memory based on information-theory is devised. The principles of the information-theory of memory are then used in conjunction with the dynamics of the linear-associator to discern its storage …

    uiuc Repository record for Storage Capacity of the Linear Associator: Beginnings of a Theory of Computational Memory (opens in a new tab)

  2. The Memory Tesseract: Developing a Unified Framework for Modelling Memory and Cognition

    Computational memory models can explain the behaviour of human memory in diverse experimental paradigms—whether it be recall or recognition, short-term or long-term retention, implicit or explicit learning. Simulation has led to parsimonious theories of memory, but at a cost of a profusion of …

    carleton Repository record for The Memory Tesseract: Developing a Unified Framework for Modelling Memory and Cognition (opens in a new tab)

  3. Ferroelectric and Monolithic 3D (M3D) Memory Technologies for High-Performance, Energy-Efficient Computing

    Present-day hardware with limited on-chip memory capacity falls short of meeting the speed and energy-efficiency requirement for data-intensive applications such as Artificial Intelligence due to the need for expensive data transfer between processor and off-chip memory. The objective of this …

    gatech Repository record for Ferroelectric and Monolithic 3D (M3D) Memory Technologies for High-Performance, Energy-Efficient Computing (opens in a new tab)

  4. Simulation of Electromagnetic Effects in Magnetic Resonance Imaging

    … technique, which dramatically reduces the computational memory requirement and the computational time, is employed to analyze the open RF coils in an MRI system. The FD-TD method, known for its ability to handle large and complex geometries, is applied to shielded birdcage coil analysis. …

    uiuc Repository record for Simulation of Electromagnetic Effects in Magnetic Resonance Imaging (opens in a new tab)

  5. Hybrid-PGAS Memory Hierarchy for Next Generation HPC Systems

    Demands on computational performance, power efficiency, data transfer, resource capacity, and resilience for next generation high performance computing (HPC) systems present a new host of challenges. There is a growing disparity between computational performance vs. network and storage device …

    maryland Repository record for Hybrid-PGAS Memory Hierarchy for Next Generation HPC Systems (opens in a new tab)

  6. Uranium-based Spintronics

    … novel solutions for the next generation of computational memory and logic devices. The combination of these heavy metals with ferromagnets can provide low energy, efficient switching of magnetisation through the spin Hall effect and spinorbit torque, or can result in interesting new chiral spin …

    bristol Repository record for Uranium-based Spintronics (opens in a new tab) Download PDF for Uranium-based Spintronics (opens in a new tab)

  7. Nova proposta de representação de genoma viral aplicada na classificação do Sars-Cov-2 com aprendizagem profunda

    … achieved satisfactory performance with low computational memory and processing time costs. Finally, given the mutation rate of RNA viruses, new variants have emerged, and within the possibility of increased cases. The technique developed was used to analyze the evolution of five variants of …

    brazil-ufrn Repository record for Nova proposta de representação de genoma viral aplicada na classificação do Sars-Cov-2 com aprendizagem profunda (opens in a new tab)

  8. The Hidden Structure of Deep Models: Discovering and Exploiting Sparse Subnetworks

    Deep learning's growing scale makes computational, memory, and communication efficiency increasingly important, and sparsity offers a principled way to improve all three. This dissertation treats sparsity as an integral component of learning in three settings: controllable sparse projection, sparse …

    gatech Repository record for The Hidden Structure of Deep Models: Discovering and Exploiting Sparse Subnetworks (opens in a new tab)

  9. Transient finite/infinite element solutions for unbounded wave problems

    … have shown that much lower solution times and computational memory overhead are required using this scheme when compared with traditional direct solutions methods. Only the non-zero terms of the system matrices need to be stored in the solution process and the solution times have been shown to …

    soton Download PDF for Transient finite/infinite element solutions for unbounded wave problems (opens in a new tab)

  10. The Spacetime Finite Element Method for Investigations into Physics Ghost Systems and Time Parallel Preconditioning

    … effective in terms of GMRES iteration count, computational memory requirements, and CPU time than that of a 1-level standard additive Schwarz method. In the final chapter, we explore the eigenvalue spectrum of the RAS system and find that a finer temporal mesh reduces the percentage of …

    sdstate Repository record for The Spacetime Finite Element Method for Investigations into Physics Ghost Systems and Time Parallel Preconditioning (opens in a new tab)

  11. Theory of the sparse grid combination technique

    … infectivity factor. In practice, when we seek a computational solution to these multi-dimensional problems, we en­counter the so-called 'curse of dimensionality." The curse of dimensionality says that the amount of resources (time and computational memory) needed to solve a problem grows …

    anu Repository record for Theory of the sparse grid combination technique (opens in a new tab)

  12. Supernormals : a floating-point format with fine-grained range control and tapered precision for DNN training

    … lower-precision floating-point formats to meet computational, memory, and energy demands. However, the use of low-precision formats in DNN training introduces severe range and precision restrictions compared to traditional floating-point standards such as IEEE 754 binary32 (FP32), which can lead …

    ubc Repository record for Supernormals : a floating-point format with fine-grained range control and tapered precision for DNN training (opens in a new tab) Download PDF for Supernormals : a floating-point format with fine-grained range control and tapered precision for DNN training (opens in a new tab)

  13. Development of substructure and superelement codes for the FEA of tall slender buildings

    … taking into consideration the need to create a computationally efficient code such that parametric studies can be performed speedily. In what follows, the current trend in tall slender buildings is discussed as well as the motivation for focusing on a structure having a regular cross-section …

    city-london Download PDF for Development of substructure and superelement codes for the FEA of tall slender buildings (opens in a new tab)

  14. Hybrid BEM-FEM for 2D and 3D dynamic soil-structure interaction considering arbitrary layered half-space and nonlinearities

    … BEM-FEM. The method significantly reduces the computational memory requirement. Another challenge in the dynamic SSI addressed in this work is the consideration of secondary nonlinearities. Existing solutions using the time domain BEM and iterative hybrid method are computationally costly, and …

    cau-kiel Repository record for Hybrid BEM-FEM for 2D and 3D dynamic soil-structure interaction considering arbitrary layered half-space and nonlinearities (opens in a new tab)

  15. Large eddy simulations of a confined rectangular jet

    … applications in the chemical process industry. Computational fluid dynamics (CFD) has the potential to be used as a tool to improve reactor designs and examine the mixing characteristics but requires extensive validation of the computational models. This research presents detailed analysis and …

    iastate Repository record for Large eddy simulations of a confined rectangular jet (opens in a new tab)

  16. Multi-Object Tracking Using Dual-Attention with Regional-Representation

    … mechanism usually causes a significant surge in computational power and memory. They also requires huge amount of epochs to train thus the training time is largely increased. To solve this issue, we propose a new method to gather non-local information based on the existing self-attention methods, …

    mcmaster Repository record for Multi-Object Tracking Using Dual-Attention with Regional-Representation (opens in a new tab)

  17. Essays in Macroeconomics and Entrepreneurship

    … Finally, in my last chapter, I present a new computational algorithm to compute distributions in heterogeneous agent models. I show how this algorithm improves on current methods by reducing the amount of computational memory and time required, and provide a simple and intuitive explanation as …

    duke Repository record for Essays in Macroeconomics and Entrepreneurship (opens in a new tab)

  18. Essays in Macroeconomics and Entrepreneurship

    … Finally, in my last chapter, I present a new computational algorithm to compute distributions in heterogeneous agent models. I show how this algorithm improves on current methods by reducing the amount of computational memory and time required, and provide a simple and intuitive explanation as …

    duke Repository record for Essays in Macroeconomics and Entrepreneurship (opens in a new tab)

  19. Formal Design and Verification of Digital PID Gain Scheduling Controllers

    … its use to realistic dynamic control systems: Computational memory runs out or available data types are not appropriate for modelling. This thesis addresses the formal design and verification of discrete PID gain-scheduled control systems. By the means of a novel abstraction methodology the …

    whiterose Download PDF for Formal Design and Verification of Digital PID Gain Scheduling Controllers (opens in a new tab)

Page 1 of 2