Sökning: "deep layers"

Visar resultat 1 - 5 av 86 avhandlingar innehållade orden deep layers.

  1. 1. Deep levels in SiC

    Författare :Franziska C. Beyer; Erik Janzén; Carl Hemmingsson; Jörg Weber; Linköpings universitet; []
    Nyckelord :NATURAL SCIENCES; NATURVETENSKAP;

    Sammanfattning : Silicon carbide (SiC) has been discussed as a promising material for high power bipolar devices for almost twenty years. Advances in SiC crystal growth especially the development of chemical vapor deposition (CVD) have enabled the fabrication of high quality material. LÄS MER

  2. 2. Network Parameterisation and Activation Functions in Deep Learning

    Författare :Martin Trimmel; Matematik LTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; deep learning; linear region; network parameterisation; activation function; network calibration; conformal predictnio; tropical algebra; rational function; temperature scaling; network symmetries;

    Sammanfattning : Deep learning, the study of multi-layered artificial neural networks, has received tremendous attention over the course of the last few years. Neural networks are now able to outperform humans in a growing variety of tasks and increasingly have an impact on our day-to-day lives. LÄS MER

  3. 3. Deep Learning Applications for Biomedical Data and Natural Language Processing

    Författare :Dennis Medved; Institutionen för datavetenskap; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; macine learning; natural language processing; heart transplantation; deep learning;

    Sammanfattning : The human brain can be seen as an ensemble of interconnected neurons, more or less specialized to solve different cognitive and motor tasks. In computer science, the term deep learning is often applied to signify sets of interconnected nodes, where deep means that they have several computational layers. LÄS MER

  4. 4. Long Term Settlements in Soft Clays

    Författare :Peter Claesson; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; calculation model; settlements; stress-strain-strain rate; consolidation; deep layers; case records; creep; lightly overconsolidated soft clay;

    Sammanfattning : When structures are founded on deep layers of lightly overconsolidated, soft clay large settlement often occur during a long period of time after completion of the structure. Therefore it is of major importance to be able to calculate and predict the expected settlements with a satisfactory degree of accuracy, as this has a great impact on the design of the foundation and the possible need for soil improvements. LÄS MER

  5. 5. Deep neural networks for electromagnetics applied to optimization and inverse problems

    Författare :Simon Stenmark; Chalmers tekniska högskola; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; calibration; optimization; Inverse problems; normalization; deep learning; neural networks;

    Sammanfattning : This thesis explores the possibilities to complement full-wave electromagnetic solvers with fully-connected neural networks. We emphasize problems that must be solved a very large number of times in a limited parameter domain. We present and evaluate the normalization method ForwardNorm. LÄS MER