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 35 for “"Tensor train"”.
-
The Tensor-Train Format and Its Applications
… In this thesis, we investigate the potential of tensor decompositions for mitigating this curse when considering systems from several application areas. Using tensor-based solvers, we directly compute numerical solutions of master equations associated with Markov processes on extremely large …
-
Fast and compact neural network via Tensor-Train reparameterization
… poses a number of challenges for deep learning training. Large neural network layers can be parameterized based on tensor decomposition to compress model size, but at the potential costs of degraded accuracy and more execution time to reconstruct the layer parameters from the tensorized …
-
Design and implementation of a convolutional neural network using tensor-train decomposition
… of the convolutional layer and verify a new training algorithm using Bayesian inference. Here we refer to any neural networks with any tensor-train-layers and trained by Bayesian training algorithm as a Bayesian TensorNet (BTN). The BTN provides a compressed network size and simplifies the …
-
Application of the Tensor Train Decomposition in Machine Learning - A Study and Tradeoffs
… multidimensional datasets are referred to as tensors. Developing efficient methods and algorithms for working with, and learning from these datasets has been the focus of recent of research. Tensor decompositions provide efficient methods for representing large tensors in more compact formats, …
-
Multi-dimensional data analytics and deep learning via tensor networks
… technology, multi-dimensional data, known as tensors, has demonstrated promising capability in capturing multidimensional correlation via efficiently extracting the latent structures, and drawn considerable attention in multiple disciplines such as image processing, recommender system, data …
-
Connecting diagrams with tensor networks
… ansatz chosen for physical reasons, such as in tensor network methods, while others (B) avoid explicit representation of quantum mechanical states entirely, thus sidestepping the problem. This thesis is about methods in both classes. The parquet equations and the functional renormalization …
-
Tensor learning with structure, geometry and multi-modality
… can be represented by multiway arrays known as tensors. For instance, a color image is athird-order tensor defined by two indices for spatial variables and one index for color mode. Someother examples include color video, medical imaging such as EEG and fMRI, spatiotemporal dataencountered in …
-
Tensor computations with dimensionality manipulations
Methodologies that ensure the compressibility of tensors are introduced. Bounds on the storage costs with respect to various tensor formats are derived. A new algorithm combining data-sparse tensor formats and factored alternating direction implicit method is designed to solve Sylvester tensor …
-
Arbitrary mode-n convolution of physical tensors with applications in optics
… could be efficiently analyzed or solved using Tensor Analysis. In Fourier Optics, convolution describes light propagation in multidimensional linear shift-invariant media and image formation in multidimensional linear shift-invariant imaging systems. In Tensor Analysis, many tensor operations, …
-
Tensor decomposition methods and their applications in dynamical systems and generative modeling
Tensors provide a unified representation for high-dimensional data arising in scientific computing, dynamical systems, and modern machine learning. This thesis develops a comprehensive framework for understanding, computing, and applying major tensor decompositions—Tucker, Canonical Polyadic (CP), …
-
Tensor product methods in numerical simulation of high-dimensional dynamical problems
… to this area in the particular direction: tensor product methods for separation of variables. The separation of variables has a long history, and is based on the following elementary concept: a function of many variables may be expanded as a product of univariate functions. On the discrete …
-
High-dimensional problems in stochastic modelling of biological processes
… addresses such computational challenges by a tensor-structured computational framework.</p> <p>After a background introduction in Chapter 1, Chapter 2 derives the order of convergence in volume size between the stationary distributions of the exact chemical master equation (CME) and its …
-
On sparse tensor structures in lattice theory and applications of the polynomial collocation method based on sparse grids
… since the invention of the computer, the use of tensors has become a more viable way to approach problems involving many variables. However, the efficient treatment of high-dimensional problems still requires special techniques such as tensor decompositions and utilizing sparsity. The first part …
-
Methods for Solving Biochemical Systems Using Moments, Maximum Entropy Reconstruction, and Machine Learning
… CME-based models by using an adaptive Quantized Tensor Train (QTT) decomposition to approximate high-dimensional solutions of biochemical systems exhibiting multi-stability, crucial for understanding phenomena such as cell signaling and disease mechanisms. Additionally, we apply machine learning …
-
A Study of Some Tensor Methods for the Chemical Master Equation
… issues. A strategy is to reformulate the FSP in tensors, i.e., multi-dimensional arrays, and represent it in quantized tensor train (QTT) format to address this challenge. This dissertation aims to show an improved algorithm of recent approaches of using a specific kind of decomposition of …
-
METHODOLOGICAL INNOVATIONS FOR CLINICAL RESEARCH: IMPROVING RELIABILITY, DATA SHARING, AND AGENTIC AI ACROSS THE EVIDENCE LIFECYCLE
… 88% for HbA1c. The second contribution, TETRiS (TEnsor-Train Enabled Regulatory Post-Marketing Surveillance), addresses data sharing and independent regulatory reanalysis. Post-marketing safety surveillance depends on real-world data, yet patient-level records are often held in proprietary …
-
Quantics Tensor Trains: The Study of a Continuous Lattice Model and Beyond
… of continuous variable functions with tensor train representation. The first chapter describes all the methodology used to discretize functions and store them efficiently. In this section, the algorithm tensor renormalization group is explained for self-containment purposes. The second …
-
Krylov approximation and model reduction methods for solving the chemical master equation
… method that is well expressed in terms of the tensor product. It employs a residual-based error control to automatically adapt the aggregation scheme to the region that requires fine details. The third tool leverages novel results in the tensor train format. It combines the finite state …
-
Functional analysis of low grade glioma genetic variants using statistics and physics-inspired deep learning methods
… interpretation methods. Finally, we applied tensor train decomposition (TT-decomposition) to neural network parameter reduction and demonstrated that the reduced convolutional neural network performed well. This work helps understand the molecular mechanisms underlying genetic risk factors of …
-
Performance Analysis of Fixed-Random Weights in Artificial Neural Networks
Deep neural networks train millions of parameters to achieve state-of-the-art performance on a wide foray of applications. However, finding a global minimum with gradient descent approaches leads to lengthy training times coupled with high computational resource requirements. To alleviate these …
Page 1 of 2