Sökning: "convolutional coding"

Visar resultat 1 - 5 av 20 uppsatser innehållade orden convolutional coding.

  1. 1. Reducing the computational complexity of a CNN-based neural network used for partitioning in VVC compliant encoders

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

    Författare :Saman Rassam; [2022]
    Nyckelord :Video Coding; VVC; Block Partitioning; VTM; ANN; CNN; Videkodning; VVC; Blockpartitionering; VTM; ANN; CNN;

    Sammanfattning : Block partitioning is a computationally heavy step in the video coding process. Previously, this stage has been done using a full-search-esque algorithm. LÄS MER

  3. 2. Polar Codes for Biometric Identification Systems

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

    Författare :Yicheng Bao; [2022]
    Nyckelord :Biometrics; Polar codes; Identification systems; Convolutional neural networks; Autoencoder; Privacy preservation; Biometri; Polära koder; Identifieringssystem; Konvolutionella neurala nätverk; Autoencoder; Sekretessskydd;

    Sammanfattning : Biometrics are widely used in identification systems, such as face, fingerprint, iris, etc. Polar code is the only code that can be strictly proved to achieve channel capacity, and it has been proved to be optimal for channel and source coding. LÄS MER

  4. 3. Improving the Robustness of Deep Neural Networks against Adversarial Examples via Adversarial Training with Maximal Coding Rate Reduction

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

    Författare :Hsiang-Yu Chu; [2022]
    Nyckelord :Machine learning; Deep neural networks; Loss function; Adversarial example; Adversarial attack; Adversarial training; Maskininlärning; Djupa neurala nätverk; Förlustfunktion; Motståndarexempel; Motståndarattack; Motståndsträning;

    Sammanfattning : Deep learning is one of the hottest scientific topics at the moment. Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. LÄS MER

  5. 4. Exploring DeepSEA CNN and DNABERT for Regulatory Feature Prediction of Non-coding DNA

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

    Författare :Jacob Stachowicz; [2021]
    Nyckelord :Machine Learning; Computer Science; Bioinformatics; Genomics; Transformer; Natural Language Processing; Whole Genome Sequencing; Non-codingDNA; DeepSEA; CNN; DNABert; BERT; DanQ; Biomedical Science; Computational Biology; AuROC; AUPRC; Maskininlärning; Datavetenskap; Bioinformatik; Genomik; Transformer; Språkteknologi; Helgenomsekvensering; icke-kod DNA; DeepSEA; CNN; DNABert; BERT; DanQ; Biomedicinsk vetenskap; Beräkningsbiologi; AuROC; AUPRC;

    Sammanfattning : Prediction and understanding of the regulatory effects of non-coding DNA is an extensive research area in genomics. Convolutional neural networks have been used with success in the past to predict regulatory features, making chromatin feature predictions based solely on non-coding DNA sequences. LÄS MER

  7. 5. Characterizing Video Compression Using Convolutional Neural Networks

    Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Datavetenskap

    Författare :Sebastian Emmot; [2020]
    Nyckelord :Neural Networks; Image Analysis; Video Analysis; Compression; Deep Learning;

    Sammanfattning : Can compression parameters used in video encoding be estimated, given only the visual information of the resulting compressed video? If so, these parameters could potentially improve existing parametric video quality estimation models. Today, parametric models use information like bitrate to estimate the quality of a given video. LÄS MER