Sökning: "faltningsnätverk"

Visar resultat 21 - 25 av 81 uppsatser innehållade ordet faltningsnätverk.

1. 21. Parameter Estimation of LPI Radar in Noisy Environments using Convolutional Neural Networks

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

   Författare :Filip Appelgren; [2021]
   Nyckelord :Deep Learning; LPI; Radar; CNN; Parameter estimation; Djupinlärning; LPI; Radar; Faltningsnätverk; Parameterestimering;

   Sammanfattning : Low-probability-of-intercept (LPI) radars are notoriously difficult for electronic support receivers to detect and identify due to their changing radar parameters and low power. Previous work has been done to create autonomous methods that can estimate the parameters of some LPI radar signals, utilizing methods outside of Deep Learning. LÄS MER

3. 22. Noisy recognition of perceptual mid-level features in music

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

   Författare :Simon Mossmyr; [2021]
   Nyckelord :;

   Sammanfattning : Self-training with noisy student is a consistency-based semi-supervised self- training method that achieved state-of-the-art accuracy on ImageNet image classification upon its release. It makes use of data noise and model noise when fitting a model to both labelled data and a large amount of artificially labelled data. LÄS MER

4. 23. Convolutional Neural Networks: Performance on Imbalanced Data

   Magister-uppsats, Umeå universitet/Statistik

   Författare :Oscar Sallander; [2021]
   Nyckelord :;

   Sammanfattning : Imbalanced data is a major problem in machine learning classification, since predictive performance can be hindered when one class occurs more frequently than the others. For example, in medical science, imbalanced data sets are very common. LÄS MER

5. 24. The Effect of Beautification Filters on Image Recognition : "Are filtered social media images viable Open Source Intelligence?"

   Magister-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Vasilios Skepetzis; Pontus Hedman; [2021]
   Nyckelord :face recognition; OSINT; machine learning; deep learning; convolutional neural networks; social media filters; u-net; residual neural network; Ansiktsigenkänning; OSINT; maskininlärning; djupinlärning; faltningsnätverk; sociala media filter; u-net; residual neuronnät;

   Sammanfattning : In light of the emergence of social media, and its abundance of facial imagery, facial recognition finds itself useful from an Open Source Intelligence standpoint. Images uploaded on social media are likely to be filtered, which can destroy or modify biometric features. LÄS MER

7. 25. Incorporating Metadata Into the Active Learning Cycle for 2D Object Detection

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

   Författare :Karsten Stadler; [2021]
   Nyckelord :Active learning; Deep Learning; Object detection; Metadata; Nuscenes Nuimages; Gaussian mixture model; Rejection sampling; Monte-Carlo methods; Aktiv Inlärning; Djupinlärning; Objektdetektering; metadata; Nuscenes Nuimages; Gaussisk blandingsmodell; Rejection sampling; Monte-Carlo metoder;

   Sammanfattning : In the past years, Deep Convolutional Neural Networks have proven to be very useful for 2D Object Detection in many applications. These types of networks require large amounts of labeled data, which can be increasingly costly for companies deploying these detectors in practice if the data quality is lacking. LÄS MER