Search for dissertations about: "CNNs"

Showing result 1 - 5 of 8 swedish dissertations containing the word CNNs.

  1. 1. Multi-LSTM Acceleration and CNN Fault Tolerance

    Author : Stefano Ribes; Chalmers University of Technology; []
    Keywords : NATURVETENSKAP; TEKNIK OCH TEKNOLOGIER; NATURAL SCIENCES; ENGINEERING AND TECHNOLOGY; Machine Learning; Fault Tolerance; LSTMs; Caffe; CNNs; SVD; Roofline Model; Compression; HLS; FPGA;

    Abstract : This thesis addresses the following two problems related to the field of Machine Learning: the acceleration of multiple Long Short Term Memory (LSTM) models on FPGAs and the fault tolerance of compressed Convolutional Neural Networks (CNN). LSTMs represent an effective solution to capture long-term dependencies in sequential data, like sentences in Natural Language Processing applications, video frames in Scene Labeling tasks or temporal series in Time Series Forecasting. READ MORE

  2. 2. DeepMaker : Customizing the Architecture of Convolutional Neural Networks for Resource-Constrained Platforms

    Author : Mohammad Loni; Mikael Sjödin; Masoud Daneshtalab; Franz Pernkopf; Mälardalens högskola; []
    Keywords : NATURAL SCIENCES; NATURVETENSKAP; NATURVETENSKAP; NATURAL SCIENCES; Computer Science; datavetenskap;

    Abstract : Convolutional Neural Networks (CNNs) suffer from energy-hungry implementation due to requiring huge amounts of computations and significant memory consumption. This problem will be more highlighted by the proliferation of CNNs on resource-constrained platforms in, e.g., embedded systems. READ MORE

  3. 3. Geometric Supervision and Deep Structured Models for Image Segmentation

    Author : Måns Larsson; Chalmers University of Technology; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; conditional random fields; convolutional neural networks; deep structured models; Semantic segmentation; self-supervised learning; supervised learning; semi-supervised learning;

    Abstract : The task of semantic segmentation aims at understanding an image at a pixel level. Due to its applicability in many areas, such as autonomous vehicles, robotics and medical surgery assistance, semantic segmentation has become an essential task in image analysis. READ MORE

  4. 4. End-to-End Learning of Deep Structured Models for Semantic Segmentation

    Author : Måns Larsson; Chalmers University of Technology; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Semantic segmentation; deep structured models; supervised learning; convolutional neural networks; conditional random fields;

    Abstract : The task of semantic segmentation aims at understanding an image at a pixel level. This means assigning a label to each pixel of an image, describing the object it is depicting. READ MORE

  5. 5. Vision-based Localization and Attitude Estimation Methods in Natural Environments

    Author : Bertil Grelsson; Michael Felsberg; Per-Erik Forssén; Joni Kämäräinen; Linköpings universitet; []
    Keywords : NATURAL SCIENCES; NATURVETENSKAP; NATURVETENSKAP; NATURAL SCIENCES;

    Abstract : Over the last decade, the usage of unmanned systems such as Unmanned Aerial Vehicles (UAVs), Unmanned Surface Vessels (USVs) and Unmanned Ground Vehicles (UGVs) has increased drastically, and there is still a rapid growth. Today, unmanned systems are being deployed in many daily operations, e.g. READ MORE