Sökning: "Convolution"

Visar resultat 1 - 5 av 54 uppsatser innehållade ordet Convolution.

  1. 1. Normalized Convolution Network and Dataset Generation for Refining Stereo Disparity Maps

    Master-uppsats, Linköpings universitet/Datorseende; Linköpings universitet/Datorseende

    Författare :Daniel Cranston; Filip Skarfelt; [2019]
    Nyckelord :Disparity Map; Disparity Refinement; Dataset Generation; Neural Network; Normalized Convolution;

    Sammanfattning : Finding disparity maps between stereo images is a well studied topic within computer vision. While both classical and machine learning approaches exist in the literature, they frequently struggle to correctly solve the disparity in regions with low texture, sharp edges or occlusions. LÄS MER

  2. 2. DSP Design With Hardware Accelerator For Convolutional Neural Networks

    Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

    Författare :Julian Hille; Lucas Santos Ferreira; [2019]
    Nyckelord :CNN; Hardware; Accelerator; DSP; Convolutional; Convolution; Neural; Network; Processor; Tensilica; FIR; Memory; SRAM; Technology and Engineering;

    Sammanfattning : Convolutional Neural Networks impressed the world in 2012 by reaching state-of-the-art accuracy levels in the ImageNet Large Scale Visual Recognition Challenge. The era of machine learning has arrived and with it countless applications varying from autonomous driving to unstructured robotic manipulation. LÄS MER

  3. 3. Detecting exoplanets with machine learning : A comparative study between convolutional neural networks and support vector machines

    Kandidat-uppsats, Uppsala universitet/Institutionen för teknikvetenskaper; Uppsala universitet/Institutionen för teknikvetenskaper; Uppsala universitet/Institutionen för teknikvetenskaper; Uppsala universitet/Institutionen för teknikvetenskaper

    Författare :Jacob Tiensuu; Maja Linderholm; Sofia Dreborg; Fredrik Örn; [2019]
    Nyckelord :Machine learning; Exoplanet; Support vector machine; Convolution neuralnetwork;

    Sammanfattning : In this project two machine learning methods, Support Vector Machine, SVM, and Convolutional Neural Network, CNN, are studied to determine which method performs best on a labeled data set containing time series of light intensity from extrasolar stars. The main difficulty is that in the data set there are a lot more non exoplanet stars than there are stars with orbiting exoplanets. LÄS MER

  4. 4. A deep learning model for scene recognition

    Kandidat-uppsats, Mittuniversitetet/Institutionen för informationssystem och –teknologi

    Författare :Zhaoxin Meng; [2019]
    Nyckelord :Scene recognition; CNN; convolutional supervised; Fisher Vector; transfer learning;

    Sammanfattning : Scene recognition is a hot research topic in the field of image recognition. It is necessary that we focus on the research on scene recognition, because it is helpful to the scene understanding topic, and can provide important contextual information for object recognition. LÄS MER

  5. 5. Sequence Models for Speech and Music Detection in Radio Broadcast

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

    Författare :Quentin Lemaire; [2019]
    Nyckelord :;

    Sammanfattning : Speech and Music detection is an important meta-data extraction step for radio broadcasters. It provides them with a good time-stamping of the audio, including parts where speech and music overlap. This task has important applications in royalty collection in broadcast audio for instance, which is the use case for this particular study. LÄS MER