Sökning: "Sparse matrix representation"

Hittade 5 uppsatser innehållade orden Sparse matrix representation.

  1. 1. Representation and Efficient Computation of Sparse Matrix for Neural Networks in Customized Hardware

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Lihao Yan; [2022]
    Nyckelord :Convolutional neural networks; Sparse matrix representation; Model compression; Algorithm-hardware co-design; AlexNet; Konvolutionella neurala nätverk; Sparsam matrisrepresentation; Modellkomprimering; Algoritm-hårdvarusamdesign; AlexNet;

    Sammanfattning : Deep Neural Networks are widely applied to various kinds of fields nowadays. However, hundreds of thousands of neurons in each layer result in intensive memory storage requirement and a massive number of operations, making it difficult to employ deep neural networks on mobile devices where the hardware resources are limited. LÄS MER

  3. 2. Convergence Properties for Different Null Space Bases When Solving the Initial Margin Optimization Problem Using CMA-ES

    Master-uppsats, KTH/Matematisk statistik

    Författare :Jacob Barnholdt; Filip Carlsson; [2020]
    Nyckelord :Financial mathematics; CMA-ES; Optimization; Initial Margin; Null space representations; Finansiell matematik; CMA-ES; Optimering; Initial Margin; Nollrumsrepresentationer;

    Sammanfattning : This thesis evaluates how the evolutionary algorithm CMA-ES (Covariance Matrix Adaption Evolution Strategy) can be used for optimizing the total initial margin for a network of banks trading bilateral OTC derivatives. The algorithm is a stochastic method for optimization of non-linear and, but not limited to, non-convex functions. LÄS MER

  4. 3. Sparse-Matrix support for the SkePU library for portable CPU/GPU programming

    Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Vishist Sharma; [2016]
    Nyckelord :Sparse Matrix; SkePU; auto tuning; CPU GPU programming; conversion function; profile guided composition;

    Sammanfattning : In this thesis work we have extended the SkePU framework by designing a new container data structure for the representation of generic two dimensional sparse matrices. Computation on matrices is an integral part of many scientific and engineering problems. Sometimes it is unnecessary to perform costly operations on zero entries of the matrix. LÄS MER

  5. 4. Random forest och glesa datarespresentationer

    Kandidat-uppsats, Högskolan i Borås/Institutionen Handels- och IT-högskolan

    Författare :Henrik Linusson; Robin Rudenwall; Andreas Olausson; [2012]
    Nyckelord :data mining; machine learning; regression; classification; in silico modeling; random forest; sparse data; feature selection;

    Sammanfattning : In silico experimentation is the process of using computational and statistical models to predict medicinal properties in chemicals; as a means of reducing lab work and increasing success rate this process has become an important part of modern drug development. There are various ways of representing molecules - the problem that motivated this paper derives from collecting substructures of the chemical into what is known as fractional representations. LÄS MER

  7. 5. Compressed Sampling for High Frequency Receivers Applications

    Master-uppsats, Avdelningen för elektronik, matematik och naturvetenskap

    Författare :xiaofei bi; [2011]
    Nyckelord :Compressive Sampling CS ; sparse representation; measurement matrix; signal reconstruction.;

    Sammanfattning : In digital signal processing field, for recovering the signal without distortion, Shannon sampling theory must be fulfilled in the traditional signal sampling. However, in some practical applications, it is becoming an obstacle because of the dramatic increase of the costs due to increased volume of the storage and transmission as a function of frequency for sampling. LÄS MER