Sökning: "nn"

Visar resultat 6 - 10 av 126 uppsatser innehållade ordet nn.

  1. 6. Cooperative Modular Neural Networks for Artificial Intelligence in Games : A Comparison with A Monolithic Neural Network Regarding Technical Aspects and The Player Experience

    Uppsats för yrkesexamina på avancerad nivå, Blekinge Tekniska Högskola/Fakulteten för datavetenskaper

    Författare :Emil Högstedt; Ove Ødegård; [2023]
    Nyckelord :Neural Network; Modularization; Sensor; Reinforcement Learning; Supervised Learning; Neuralt Nätverk; Modulärisering; Sensor; Förstärkningsinlärning; Väglett Lärande;

    Sammanfattning : Recent years have seen multiple machine-learning research projects concerning agents in video games. Yet, there is a disjoint between this academic research and the video game industry, evidenced by the fact that game developers still hesitate to use neural networks (NN) due to lack of clarity and control. LÄS MER

  2. 7. Dataset Drift in Radar Warning Receivers : Out-of-Distribution Detection for Radar Emitter Classification using an RNN-based Deep Ensemble

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

    Författare :Kevin Coleman; [2023]
    Nyckelord :Radar Emitter Classification; Pulse Descriptor Word; Out of Distribution Detection; Dataset Drift; Uncertainty Estimation; Deep Ensembles; Recurrent Neural Networks; LSTM;

    Sammanfattning : Changes to the signal environment of a radar warning receiver (RWR) over time through dataset drift can negatively affect a machine learning (ML) model, deployed for radar emitter classification (REC). The training data comes from a simulator at Saab AB, in the form of pulsed radar in a time-series. LÄS MER

  3. 8. Toward an application of machine learning for predicting foreign trade in services – a pilot study for Statistics Sweden

    Master-uppsats, Stockholms universitet/Statistiska institutionen

    Författare :Tea Unnebäck; [2023]
    Nyckelord :foreign trade in services; sampling; sampling frame; statistics; machine learning; random forest; predicting; extreme gradient boosting; k nearest neighbors; k-nn; official statistics; statistics sweden;

    Sammanfattning : The objective of this thesis is to investigate the possibility of using machine learn- ing at Statistics Sweden within the Foreign Trade in Services (FTS) statistic, to predict the likelihood of a unit to conduct foreign trade in services. The FTS survey is a sample survey, for which there is no natural frame to sample from. LÄS MER

  4. 9. Cellular Automata as Synthetic Training Data : Exploring behavioural patterns of neural networks

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Onur Yüksel; [2023]
    Nyckelord :;

    Sammanfattning : On the highest heights of the third AI spring where the interest in AI research and industrial applications is booming, it’s worth taking a step back to reexplore the basics. With the spirit of data-centric-ai, we discuss the use of Cellular Automata as a resource for synthetic training data and explore how properties of CA rules relate to learning. LÄS MER

  5. 10. Through the Blur with Deep Learning : A Comparative Study Assessing Robustness in Visual Odometry Techniques

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

    Författare :Alexander Berglund; [2023]
    Nyckelord :artificial intelligence; AI; machine learning; ML; deep learning; DL; computer vision; neural networks; NN; convolutional neural networks; CNN; visual odometry; VO; robustness; motion blur; AirForestry; localization; navigation; ego-motion; pose estimation; SLAM; DF-VO; DytanVO; ORB-SLAM3; artificiell intelligens; maskininlärning; datorseende;

    Sammanfattning : In this thesis, the robustness of deep learning techniques in the field of visual odometry is investigated, with a specific focus on the impact of motion blur. A comparative study is conducted, evaluating the performance of state-of-the-art deep convolutional neural network methods, namely DF-VO and DytanVO, against ORB-SLAM3, a well-established non-deep-learning technique for visual simultaneous localization and mapping. LÄS MER