Sökning: "nn"

Visar resultat 21 - 25 av 126 uppsatser innehållade ordet nn.

  1. 21. Evaluation of the performance of machine learning techniques for email classification

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

    Författare :Isabella Tapper; [2022]
    Nyckelord :Natural Language Processing; Text Representations; Email Classification; Text Classification; Behandling Av Naturliga Språk; Text Representation; epost-klassificering; Textklassificering;

    Sammanfattning : Manual categorization of a mail inbox can often become time-consuming. Therefore many attempts have been made to use machine learning for this task. One essential Natural Language Processing (NLP) task is text classification, which is a big challenge since an NLP engine is not a native speaker of any human language. LÄS MER

  3. 22. Path and Route Planning for Indoor Monitoring with UAV : An Evaluation of Algorithms for Time-constrained Path and Route Planning in an Indoor Environment with Several Waypoints and Limited Battery Time

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

    Författare :Ola Johansson; [2022]
    Nyckelord :UAV; path planning; route planning; drone; combinatorial optimization; Ruttplanering; banplanering; vägplanering drönare; kombinatorisk optimisering;

    Sammanfattning : Unmanned flying vehicles (UAVs) are tools that can be used in a variety of scenarios. The most common areas of application are outdoors, where there are not many obstacles to take into consideration when planning a route. LÄS MER

  4. 23. A Study on Fault Tolerance of Image Sensor-based Object Detection in Indoor Navigation

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

    Författare :Yang Wang; [2022]
    Nyckelord :Gazebo; YOLO; Object detection; Fault tolerance; Fault Injection; Network pruning; Gazebo; YOLO; Objektdetektering; Feltolerans; Felinjektion; Nätverk beskärning;

    Sammanfattning : With the fast development of embedded deep-learning computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying NN onto the devices under complex environments, there are various types of possible faults: soft errors caused by cosmic radiation and radioactive impurities, voltage instability, aging, temperature variations, etc. LÄS MER

  5. 24. Benchmarking Deep Reinforcement Learning on Continuous Control Tasks : AComparison of Neural Network Architectures and Environment Designs

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

    Författare :Daniel Sahlin; [2022]
    Nyckelord :Deep learning; Reinforcement learning; Reward functions; Neural networks; Furuta pendulum; Djupinlärning; Förstärkningsinlärning; Belöningsfunktioner; Neurala nätverk; Furuta-pendel;

    Sammanfattning : Deep Reinforcement Learning (RL) has received much attention in recent years. This thesis investigates how reward functions, environment termination conditions, Neural Network (NN) architectures, and the type of the deep RL algorithm aect the performance for continuous control tasks. LÄS MER

  7. 25. Probabilistic Detection of Nuclei in Digital Pathology using Bayesian Deep Learning

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Chuxin Zhang; [2022]
    Nyckelord :Uncertainty Estimation; Bayesian Deep Learning; Monte-Carlo Dropout; Digital Pathology;

    Sammanfattning : Deep learning (DL) has demonstrated outstanding performance in a variety of applications. With the assistance of DL, healthcare seeks to reduce labor costs and increase access to high-quality medical resources. To ensure the stability and robustness of DL applications in medicine, it is essential to estimate the uncertainty. LÄS MER