Sökning: "LeNet"

Visar resultat 1 - 5 av 9 uppsatser innehållade ordet LeNet.

  1. 1. Investigation of Facial Age Estimation using Deep Learning

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Lufei Ye; [2022]
    Nyckelord :;

    Sammanfattning : Age estimation from facial images has drawn increasing attention in the past fewyears. This thesis project performs the age group classification of facial imagesacquired in in-the-wild conditions using deep convolutional neural networkstechniques. LÄS MER

  3. 2. Effects of Local Data Distortion in Federated Learning

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Fredrik Peteri Harr; [2022]
    Nyckelord :federated learning; machine learning; neural networks; distortion;

    Sammanfattning : This study explored how clients with distorted data affected the Federated Learning process using the FedAvg and FedProx algorithms. Different amounts of the three distortions, Translation, Rotation, and Blur, were tested using three different Machine Learning models. LÄS MER

  4. 3. Evaluating Robustness of a CNN Architecture introduced to the Adversarial Attacks

    Kandidat-uppsats, Blekinge Tekniska Högskola

    Författare :Shaik Ishak; Anantaneni Jyothsna Chowdary; [2021]
    Nyckelord :Convolutional Neural Network CNN ; Image classification; Adversarial attacks; Defensive Distillation.;

    Sammanfattning : Abstract: Background: From Previous research, state-of-the-art deep neural networks have accomplished impressive results on many images classification tasks. However, adversarial attacks can easily fool these deep neural networks by adding little noise to the input images. LÄS MER

  5. 4. A Low Power AI Inference Accelerator for IoT Edge Computing

    Master-uppsats, Linköpings universitet/Datorteknik

    Författare :Olle Hansson; [2021]
    Nyckelord :low power; artificial intelligence; AI; inference accelerator; internet of things; IoT; edge computing; machine learning; ML;

    Sammanfattning : This thesis investigates the possibility of porting a neural network model trained and modeled in TensorFlow to a low-power AI inference accelerator for IoT edge computing. A slightly modified LeNet-5 neural network model is presented and implemented such that an input frequency of 10 frames per second is possible while consuming 4mW of power. LÄS MER

  7. 5. A Deep Learning Application for Traffic Sign Recognition

    Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Pramod Sai Kondamari; Anudeep Itha; [2021]
    Nyckelord :Image Processing; Deep Learning Algorithms; Convolutional Neural Network CNN ; OpenCV; Supervised Learning.;

    Sammanfattning : Background: Traffic Sign Recognition (TSR) is particularly useful for novice driversand self-driving cars. Driver Assistance Systems(DAS) involves automatic trafficsign recognition. Efficient classification of the traffic signs is required in DAS andunmanned vehicles for safe navigation. LÄS MER