Search for dissertations about: "CNN"

Showing result 1 - 5 of 42 swedish dissertations containing the word CNN.

  1. 1. Automated CNN pipeline generation for heterogeneous architectures

    Author : Pirah Noor Soomro; Chalmers tekniska högskola; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Online tuning; CNN parallel pipelines; Heterogeneous computing units; Processing on chiplets; Design space exploration;

    Abstract : Heterogeneity is a vital feature in emerging processor chip designing. Asymmetric multicore-clusters such as high-performance cluster and power efficient cluster are common in modern edge devices. One example is Intel's Alder Lake featuring Golden Cove high-performance cores and Gracemont power-efficient cores. READ MORE

  2. 2. Non-enhanced single-energy computed tomography of urinary stones

    Author : Johan Jendeberg; Mats Lidén; Per Thunberg; Anders Magnusson; Örebro universitet; []
    Keywords : MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Diagnostic; CT; urinary stone; kidney stone; urolithiasis; phlebolith; uric acid; spontaneous passage; CNN; artificial intelligence;

    Abstract : Computed tomography (CT) is the mainstay imaging method for urinary stones.The aim of this thesis was to optimize the information obtained from the initial CT scan to allow a well-founded diagnosis and prognosis, and to guide the clinician as early and as far as possible in the further treatment of urinary stone disease. READ MORE

  3. 3. Automatic Melanoma Diagnosis in Dermoscopic Imaging Base on Deep Learning System

    Author : Yali Nie; Jan Lundgren; Mattias O'Nils; Claes Lundström; Mittuniversitetet; []
    Keywords : MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Melanoma classification; computer vision; Deep learning; CNN;

    Abstract : Melanoma is one of the deadliest forms of cancer. Unfortunately, its incidence rates have been increasing all over the world. One of the techniques used by dermatologists to diagnose melanomas is an imaging modality called dermoscopy. The skin lesion is inspected using a magnification device and a light source. READ MORE

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

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

    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

  5. 5. Strategies of power in multilingual global broadcasters : How the BBC, CNN and Aljazeera shape their Middle East news discourse

    Author : Leon Barkho; Lars-Åke Engblom; Robert Picard; Golam Rahman; Jönköping University; []
    Keywords : SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Media and communication studies; Medie- och kommunikationsvetenskap; Middle East; Mellanöstern;

    Abstract :  This study deals with the Middle East reporting of three gigantic media companies which together are largely responsible for refining and shaping our views of events in the world. The informational and communicative arm of these giants – Aljazeera, the BBC and CNN – is unprecedented in the history of human communication. READ MORE