Sökning: "inlärningsmodeller"

Visar resultat 1 - 5 av 18 uppsatser innehållade ordet inlärningsmodeller.

1. 1. Exploration and Evaluation of RNN Models on Low-Resource Embedded Devices for Human Activity Recognition

   Master-uppsats, KTH/Mekatronik och inbyggda styrsystem

   Författare :Helgi Hrafn Björnsson; Jón Kaldal; [2023]
   Nyckelord :Recurrent Neural Networks; Long Short-Term Memory Networks; Embedded Systems; Human Activity Recognition; Edge AI; TensorFlow Lite Micro; Recurrent Neural Networks; Long Short-Term Memory Networks; Innbyggda systyem; Mänsklig aktivitetsigenkänning; Edge AI; TensorFlow Lite Micro;

   Sammanfattning : Human activity data is typically represented as time series data, and RNNs, often with LSTM cells, are commonly used for recognition in this field. However, RNNs and LSTM-RNNs are often too resource-intensive for real-time applications on resource constrained devices, making them unsuitable. LÄS MER

3. 2. Evaluating the Effects of Neural Noise in the Multidigraph Learning Rule

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

   Författare :Gustav Bressler; Sigvard Dackevall; [2023]
   Nyckelord :;

   Sammanfattning : There exists a knowledge gap in the field of Computational Neuroscience, where many learning models for neural networks fail to take into account the influence of neural noise. The purpose of this thesis was to address this knowledge gap by investigating the robustness of the Multidigraph learning rule (MDGL) when exposed to two kinds of neural noise: external noise and internal noise. LÄS MER

4. 3. A comparative evaluation of machine learning models for engagement classification during presentations : A comparison of distance- and non-distance-based machine learning models for presentation classification and class likelihood estimation

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

   Författare :Rebwar Ali Omer Bajallan; [2022]
   Nyckelord :Audience engagement; Engagement quantification; Machine learning; Distance-based models; Few-shot learning; Statistical analysis; Publiksengagemang; Engagemangskvantifiering; Maskininlärning; Distansbaserade modeller; Few-shot inlärning; Statistisk analys;

   Sammanfattning : In recent years, there has been a significant increase in the usage of audience engagement platforms, which have allowed for engaging interactions between presenters and their audiences. The increased popularity of the platforms comes from the fact that engaging and interactive presentations have been shown to improve learning outcomes and create positive presentation experiences. LÄS MER

5. 4. Real-time object detection robotcontrol : Investigating the use of real time object detection on a Raspberry Pi for robot control

   Magister-uppsats, KTH/Skolan för industriell teknik och management (ITM)

   Författare :Simon Ryberg; Jonathan Jansson; [2022]
   Nyckelord :Edge Device Raspberry Pi Image recognition Machine learning Tracked robot Track drive; Edge device Raspberry Pi Maskin inlärning Bandvagns robot Band drivlina Bildigenkänning;

   Sammanfattning : The field of autonomous robots have been explored more and more over the last decade. The combination of machine learning advances and increases in computational power have created possibilities to explore the usage of machine learning models on edge devices. LÄS MER

7. 5. Improving the Robustness of Deep Neural Networks against Adversarial Examples via Adversarial Training with Maximal Coding Rate Reduction

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

   Författare :Hsiang-Yu Chu; [2022]
   Nyckelord :Machine learning; Deep neural networks; Loss function; Adversarial example; Adversarial attack; Adversarial training; Maskininlärning; Djupa neurala nätverk; Förlustfunktion; Motståndarexempel; Motståndarattack; Motståndsträning;

   Sammanfattning : Deep learning is one of the hottest scientific topics at the moment. Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. LÄS MER