Sökning: "Neural Networks"

Visar resultat 1 - 5 av 369 avhandlingar innehållade orden Neural Networks.

  1. 1. Uncertainties in Neural Networks : A System Identification Approach

    Författare :Magnus Malmström; Fredrik Gustafsson; Isaac Skog; Daniel Axehill; Håkan Hjalmarsson; Linköpings universitet; []
    Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; neural networks; uncertainty; system identification;

    Sammanfattning : In science, technology, and engineering, creating models of the environment to predict future events has always been a key component. The models could be everything from how the friction of a tire depends on the wheels slip  to how a pathogen is spread throughout society. LÄS MER

  2. 2. Artificial neural networks : applications in morphometric and landscape features analysis

    Författare :Amir Houshang Ehsani; Fredrich Quiel; Wolter Arnberg; KTH; []
    Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Environmental engineering; Miljöteknik;

    Sammanfattning : In this thesis a semi-automatic method is developed to analyze morphometric features and landscape elements based on Self Organizing Map (SOM) as a unsupervised Artificial Neural Network algorithm. Analysis and parameterization of topography into simple and homogenous land elements (landform) can play an important role as basic information in planning processes and environmental modeling. LÄS MER

  3. 3. Towards Cortex Isomorphic Attractor Neural Networks

    Författare :Christopher Johansson; KTH; []
    Nyckelord :Attractor Neural Networks; Cerebral Cortex; Minicolumns; Hypercolumns; Potts Neural Networks; BCPNN; and Parallel Computers;

    Sammanfattning : In this thesis we model the mammalian cerebral cortex withattractor neural networks and study the parallelimplementations of these models. First, we review the size, structure, and scaling laws ofthe cerebral cortex of five mammals; mouse, rat, cat, macaque,and human. LÄS MER

  4. 4. G-equivariant convolutional neural networks

    Författare :Jimmy Aronsson; Chalmers University of Technology; []
    Nyckelord :symmetry; deep learning; convolutional neural networks; homogeneous spaces; induced representations; homogeneous vector bundles;

    Sammanfattning : Over the past decade, deep learning has revolutionized industry and academic research. Neural networks have been used to solve a multitude of previously unsolved problems and to significantly improve the state-of-the-art on other tasks, in some cases reaching superhuman levels of performance. LÄS MER

  5. 5. Characterizing Piecewise Linear Neural Networks

    Författare :Anton Johansson; Chalmers University of Technology; []
    Nyckelord :NATURVETENSKAP; NATURVETENSKAP; NATURAL SCIENCES; NATURAL SCIENCES; machine learning; piecewise linear; neural network; automotive applications.;

    Sammanfattning : Neural networks utilizing piecewise linear transformations between layers have in many regards become the default network type to use across a wide range of applications. Their superior training dynamics and generalization performance irrespective of the nature of the problem has resulted in these networks achieving state of the art results on a diverse set of tasks. LÄS MER