Sökning: "Resnet"

Visar resultat 16 - 20 av 84 uppsatser innehållade ordet Resnet.

1. 16. Straight to the Heart : Classification of Multi-Channel ECG-signals using MiniROCKET

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

   Författare :Stefan Christiansson; [2023]
   Nyckelord :MiniROCKET; Time-series analysis; Multi-variate; Classification; Convolutional Neural Network; MiniROCKET; Tidsserieanalys; Multivariat; Klassifikation; Convolutional Neural Network;

   Sammanfattning : Machine Learning (ML) has revolutionized various domains, with biomedicine standing out as a major beneficiary. In the realm of biomedicine, Convolutional Neural Networks (CNNs) have notably played a pivotal role since their inception, particularly in applications such as time-series classification. LÄS MER

3. 17. Using Reinforcement Learning to Correct Soft Errors of Deep Neural Networks

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

   Författare :Yuhang Li; [2023]
   Nyckelord :DNN; Soft errors; Redundancy; DRL; DQN; Transfer learning; Training time; DNN; Mjuka fel; Redundans; DRL; DQN; Överföringsinlärning; Utbildningstid;

   Sammanfattning : Deep Neural Networks (DNNs) are becoming increasingly important in various aspects of human life, particularly in safety-critical areas such as autonomous driving and aerospace systems. However, soft errors including bit-flips can significantly impact the performance of these systems, leading to serious consequences. LÄS MER

4. 18. Unsupervised Domain Adaptation for Regressive Annotation : Using Domain-Adversarial Training on Eye Image Data for Pupil Detection

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

   Författare :Erik Zetterström; [2023]
   Nyckelord :Neural networks; Deep learning; Convolutional neural networks; Transfer learning; Domain adaptation; Unsupervised training; Adversarial training; Keypoint detection; Regression; Neurala nätverk; Djupinlärning; Faltningsnätverk; Överförningsinlärning; Domänadaptering; Oövervakad inlärning; Motstående träning; Nyckelpunktsdetektion; Regression;

   Sammanfattning : Machine learning has seen a rapid progress the last couple of decades, with more and more powerful neural network models continuously being presented. These neural networks require large amounts of data to train them. LÄS MER

5. 19. 3D Gaze Estimation on RGB Images using Vision Transformers

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

   Författare :Jing Li; [2023]
   Nyckelord :3D Gaze Estimation; Vision Transformers ViTs ; Convolutional Neural Networks CNNs ; Multi-Head Attention; Red-Green-Blue RGB Images; 3D Blickriktningsestimering; Vision Transformers ViTs ; Konvolutionsneurala Nätverk CNNs ; Multi-Head Attention; Röd-Grön-Blå RGB Bilder;

   Sammanfattning : Gaze estimation, a vital component in numerous applications such as humancomputer interaction, virtual reality, and driver monitoring systems, is the process of predicting the direction of an individual’s gaze. The predominant methods for gaze estimation can be broadly classified into intrusive and nonintrusive approaches. LÄS MER

7. 20. Selective Kernel Network based Crowding Counting and Crowd Density Estimation

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

   Författare :Jinchen Liu; [2023]
   Nyckelord :Crowding Counting; Convolution Neural Network; Selective kernel; Trängselräkning; konvolutionsneuralnätverk; Selektiv kärna;

   Sammanfattning : Managing crowd density has become an immense challenge for public authorities due to population growth and evolving human dynamics. Crowd counting estimates the number of individuals in a given area or scene, making it a practical technique applicable in real-world scenarios such as surveillance and traffic control. LÄS MER