Sökning: "hyper-parameter optimization"

Visar resultat 1 - 5 av 12 uppsatser innehållade orden hyper-parameter optimization.

  1. 1. Facial Emotion Recognition using Convolutional Neural Network with Multiclass Classification and Bayesian Optimization for Hyper Parameter Tuning.

    Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Lokesh Bejjagam; Reshmi Chakradhara; [2022]
    Nyckelord :Computing Methodologies; Machine Learning; Machine Learning Approaches; Convolutional Neural Network; Facial Emotion Recognition.;

    Sammanfattning : The thesis aims to develop a deep learning model for facial emotion recognition using Convolutional Neural Network algorithm and Multiclass Classification along with Hyper-parameter tuning using Bayesian Optimization to improve the performance of the model. The developed model recognizes seven basic emotions in images of human beings such as fear, happy, surprise, sad, neutral, disgust and angry using FER-2013 dataset. LÄS MER

  3. 2. Facial Emotion Recognition by Hyper-Parameter tuning of Convolutional Neural Network using Genetic Algorithm

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Satyachandra Saurabh Bellamkonda; [2021]
    Nyckelord :;

    Sammanfattning : Context: Importance of facial emotion recognition is increasing significantly as it's applications play a key role in several sectors and fields. Deep learning techniques in machine learning provide good performance in facial recognition tasks, Where as deep neural networks like convolutional neural networks are most widely used for image recognition and classification tasks. LÄS MER

  4. 3. Bayesian Parameter Tuning of the Ant Colony Optimization Algorithm : Applied to the Asymmetric Traveling Salesman Problem

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

    Författare :Emmy Yin; Klas Wijk; [2021]
    Nyckelord :;

    Sammanfattning : The parameter settings are vital for meta-heuristics to be able to approximate the problems they are applied to. Good parameter settings are difficult to find as there are no general rules for finding them. Hence, they are often manually selected, which is seldom feasible and can give results far from optimal. LÄS MER

  5. 4. Extension of Machine Learning Model for Dynamic Risk Analysis

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

    Författare :Björn Seifert; [2021]
    Nyckelord :Machine Learning;

    Sammanfattning : During this study a model for predicting the next week's alarm codes based on the past week's alarm codes was developed. The model used alarm data from the location and its surroundings. LÄS MER

  7. 5. Bayesian Optimization for Neural Architecture Search using Graph Kernels

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

    Författare :Bharathwaj Krishnaswami Sreedhar; [2020]
    Nyckelord :Neural architecture search; Bayesian optimization; Graph kernels; Graph convolutional networks; Neural architecture search; Bayesian optimization; Graph kernels; Graph convolutional networks;

    Sammanfattning : Neural architecture search is a popular method for automating architecture design. Bayesian optimization is a widely used approach for hyper-parameter optimization and can estimate a function with limited samples. LÄS MER