Sökning: "Slumpmässig sökning."

Visar resultat 6 - 10 av 12 uppsatser innehållade orden Slumpmässig sökning..

  1. 6. 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

  3. 7. Hyperparameter optimisation using Q-learning based algorithms

    Master-uppsats, Karlstads universitet/Fakulteten för hälsa, natur- och teknikvetenskap (from 2013)

    Författare :Daniel Karlsson; [2020]
    Nyckelord :Hyperparameter optimisation; Reinforcement learning; Convolutional neural networks; Hyperparameteroptimering; Förstärkningsinlärning; Faltande neurala nätverk;

    Sammanfattning : Machine learning algorithms have many applications, both for academic and industrial purposes. Examples of applications are classification of diffraction patterns in materials science and classification of properties in chemical compounds within the pharmaceutical industry. LÄS MER

  4. 8. Hyperparameter Optimization for Convolutional Neural Networks

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

    Författare :Clément Gousseau; [2020]
    Nyckelord :;

    Sammanfattning : Training algorithms for artificial neural networks depend on parameters called the hyperparameters. They can have a strong influence on the trained model but are often chosen manually with trial and error experiments. LÄS MER

  5. 9. A Reward-based Algorithm for Hyperparameter Optimization of Neural Networks

    Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

    Författare :Olov Larsson; [2020]
    Nyckelord :Convolutional Neural Networks; Reinforcement Learning; Hyperparameter Optimization; Faltande Neurala Nätverk; Förstärkningsinlärning; Hyperparameteroptimering;

    Sammanfattning : Machine learning and its wide range of applications is becoming increasingly prevalent in both academia and industry. This thesis will focus on the two machine learning methods convolutional neural networks and reinforcement learning. LÄS MER

  7. 10. Learning-Based Auto-Tuning for Motion Controllers of Mobile Robots

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

    Författare :Jonathan Blixt; [2019]
    Nyckelord :;

    Sammanfattning : An auto-tuner of the parameters of a mobile robots motion controlleris developed to improve its performance. The generality of the auto-tunerallows for similar applications on other robots or controllers. LÄS MER