Sökning: "DNN"

Visar resultat 1 - 5 av 71 uppsatser innehållade ordet DNN.

  1. 1. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Sofia Leksell; [2024]
    Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

    Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

  3. 2. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

    Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronik

    Författare :Sofia Leksell; [2024]
    Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

    Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

  4. 3. The Impact of Deep Neural Network Pruning on the Hyperparameter Performance Space: An Empirical Study

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Jonna Matthiesen; [2023-10-24]
    Nyckelord :Compression; Deep Learning; DNN; Hyperparameters; Optimization; Pruning; Hyperparameter Optimisation; Hyperparameter Tuning;

    Sammanfattning : With the continued growth of deep learning models in terms of size and computational requirements, the need for efficient models for deployment on resource-constrained devices becomes crucial. Structured pruning has emerged as a proven method to speed up models and reduce computational requirements. LÄS MER

  5. 4. EMONAS : Evolutionary Multi-objective Neuron Architecture Search of Deep Neural Network

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

    Författare :Jiayi Feng; [2023]
    Nyckelord :DNN Deep Neural Network ; NAS Neural Architecture Search ; EA Evolutionary Algorithm ; Multi-Objective Optimization; Binary One Optimization; Embedded Systems; DNN Deep Neural Network ; NAS Neural Architecture Search ; EA Evolutionary Algorithm ; Multi-Objective Optimization; Binary One Optimization; Inbyggda system;

    Sammanfattning : Customized Deep Neural Network (DNN) accelerators have been increasingly popular in various applications, from autonomous driving and natural language processing to healthcare and finance, etc. However, deploying them directly on embedded system peripherals within real-time operating systems (RTOS) is not easy due to the paradox of the complexity of DNNs and the simplicity of embedded system devices. LÄS MER

  7. 5. Deep Learning Based Sentiment Analysis

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Shashank Kalluri; [2023]
    Nyckelord :Sentiment Analysis; Word Embedding; Deep Learning;

    Sammanfattning : Background: Text data includes things like customer reviews and complaints,tweets from social media platforms. When analyzing text-based data, the SentimentModel is used. Understanding news headlines, blogs, the stock market, politicaldebates, and film reviews some of the areas where sentiment analysis is used. LÄS MER