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 16 of 16 for “"Kernel Matrix"”.

  1. Semi-Parametric Testing of Single-Nucleotide Polymorphism Effects On Continuous Outcome

    … we explored a semi-parametric method built upon kernel machines to include multiple SNPs in a model. The information of SNPs similarity calculated based on identity-by-state (IBS) algorithm was included in a kernel matrix. We evaluated the method via various scenarios based on simulation studies. …

    south-carolina Repository record for Semi-Parametric Testing of Single-Nucleotide Polymorphism Effects On Continuous Outcome (opens in a new tab)

  2. Application of wavelets in few-body problems.

    … is used to discretize the problem into a dense matrix. Wavelets are a class of functions with special properties. Daubachies wavelets are a subset of wavelets defined to have vanishing lower order moments, enabling Daubachies 2 and 3 wavelet bases to exactly represent polynomials of degree up to …

    umn Repository record for Application of wavelets in few-body problems. (opens in a new tab)

  3. Diversity-inducing probability measures for machine learning

    … problems arise in machine learning within kernel approximation, experimental design, and numerous other applications. In such applications, one often seeks to select diverse subsets of items to represent the population. One way to select such diverse subsets is to sample according to …

    mit Repository record for Diversity-inducing probability measures for machine learning (opens in a new tab)

  4. Efficient schemes on solving fractional integro-differential equations

    … expression of Genocchi polynomial operational matrix for left-sided and right-sided Caputo’s derivative and kernel matrix has been derived. Linear independence of Genocchi polynomials has been proved by deriving the expression for Genocchi polynomial Gram determinant. Genocchi polynomial method …

    uthm Repository record for Efficient schemes on solving fractional integro-differential equations (opens in a new tab)

  5. Integrating Multiple Data Views for Improved Malware Analysis

    … met is that a positive semidefinite similarity (kernel) matrix must be defined on the view, a restriction that is easily met in practice. While the classification problem can be solved with well known multiple kernel learning techniques, the clustering and phylogenetic problems required the …

    unm Repository record for Integrating Multiple Data Views for Improved Malware Analysis (opens in a new tab)

  6. COMPOSITE KERNEL FEATURE ANALYSIS FOR CANCER CLASSIFICATION

    … Our studies are focused in developing a fast kernel feature analysis that can efficiently differentiate polyps from false positives and thus improve the detection performance of polyps. We have developed a novel method of selecting kernel functions that are appropriate for the given data set …

    vcu Repository record for COMPOSITE KERNEL FEATURE ANALYSIS FOR CANCER CLASSIFICATION (opens in a new tab)

  7. Low rank methods for optimizing clustering

    … We utilize low rank structures in the solution matrix of the convex formulation and use a low-rank factorization of the solution matrix directly as a practical alternative. The resulting optimization problem is non-convex, but has a smaller number of solution variables, and can be locally …

    purdue-thes Repository record for Low rank methods for optimizing clustering (opens in a new tab)

  8. Efficient sampling for determinantal point processes

    … chain (k-)DPP under the condition that data kernel matrix is sparse. Concretely, we present a general framework for accelerating algorithms that requires computation of uT A-1u as one of computational subroutines. In our framework, we bound uT A-1u with Gauss-type quadrature efficiently. We …

    mit Repository record for Efficient sampling for determinantal point processes (opens in a new tab)

  9. Scalable Approximate Inference and Model Selection in Gaussian Process Regression

    … datasets due to the need to compute a large kernel matrix and perform standard linear-algebraic operations with this matrix. This limitation has driven decades of research in both statistics and machine learning seeking to scale Gaussian process regression models to ever-larger datasets. This …

    cambridge Repository record for Scalable Approximate Inference and Model Selection in Gaussian Process Regression (opens in a new tab)

  10. Complex data analytics via sparse, low-rank matrix approximation

    … 1) we develop Exemplar-based low-rank sparse Matrix Decomposition (EMD), a novel method for fast clustering large-scale data by incorporating low-rank approximations into matrix decomposition-based clustering; 2) we propose ECKF, a general model for large-scale Evolutionary Clustering based on …

    wayne-thes Repository record for Complex data analytics via sparse, low-rank matrix approximation (opens in a new tab)

  11. Modified Kernel Principal Component Analysis and Autoencoder Approaches to Unsupervised Anomaly Detection

    … in two existing anomaly detection algorithms, Kernel Principal Component Analysis (KPCA) and Autoencoders (AE), and proposes novel solutions to improve both of their performances in the unsupervised settings. Anomaly detection has several useful applications, such as intrusion detection, fault …

    vt Repository record for Modified Kernel Principal Component Analysis and Autoencoder Approaches to Unsupervised Anomaly Detection (opens in a new tab)

  12. Invariant embeddings of the Deligne-Lusztig curves with applications

    … of algebraic geometry codes as suitable kernels for channel polarization. We show that for a family of AG-codes of block length $L$ and kernel matrix $G_L$, that the exponent $E(G_L)\to 1$ as $L \to \infty$. We also compare how the binary concatenated Reed-Solomon, Hermitian, and Suzuki …

    uiuc Repository record for Invariant embeddings of the Deligne-Lusztig curves with applications (opens in a new tab)

  13. Aerosol nanoparticle size spectrometry and classification methods based on corona unipolar charging.

    … Three different methods are adapted for a dot-matrix approach to the problem, especially for non-square or singular matrices, and applied to the electrical mobility measurements from fixed or scanning voltages. Multiple charged particles, diffusion losses, arbitrary voltage steps and noise have …

    oviedo Repository record for Aerosol nanoparticle size spectrometry and classification methods based on corona unipolar charging. (opens in a new tab)

  14. Polar Coding in Certain New Transmission Environments

    Polar codes, introduced by Arikan in 2009, have attracted considerable interest as an asymptotically capacity-achieving code with sufficient performance advantages to merit inclusion in the 5G standard. Polar codes are constructed directly from an explicit model of the communication channel, so …

    vt Repository record for Polar Coding in Certain New Transmission Environments (opens in a new tab)

  15. Convergence Rates of Spectral Distribution of Random Inner Product Kernel Matrices

    … the first part, we focus on random inner product kernel matrices. Under various assumptions, many authors have proved that the limiting empirical spectral distribution (ESD) of such matrices A converges to the Marchenko- Pastur distribution. Here, we establish the corresponding rate of …

    temple Repository record for Convergence Rates of Spectral Distribution of Random Inner Product Kernel Matrices (opens in a new tab)

  16. Algorithmic Distribution of Applied Learning on Big Data

    … This approach is not feasible in numerous kernel, matrix, optimization, graph, and other techniques where the algorithm needs access to all the data during execution. In this work, we propose key-value pair based distribution techniques that are widely applicable to statistical machine …

    vt Repository record for Algorithmic Distribution of Applied Learning on Big Data (opens in a new tab)