Sökning: "förlustfunktion"

Visar resultat 1 - 5 av 26 uppsatser innehållade ordet förlustfunktion.

1. 1. Heart rate estimation from wrist-PPG signals in activity by deep learning methods

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

   Författare :Marie-Ange Stefanos; [2023]
   Nyckelord :Deep Learning; Medical Data; Signal Processing; Heart Rate Estimation; Wrist Photoplethysmography; Djup lärning; Medicinska Data; Signalbehandling; Pulsuppskattning; Handledsfotopletysmograf;

   Sammanfattning : In the context of health improving, the measurement of vital parameters such as heart rate (HR) can provide solutions for health monitoring, prevention and screening for certain chronic diseases. Among the different technologies for HR measuring, photoplethysmography (PPG) technique embedded in smart watches is the most commonly used in the field of consumer electronics since it is comfortable and does not require any user intervention. LÄS MER

3. 2. Biodiversity Monitoring Using Machine Learning for Animal Detection and Tracking

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

   Författare :Qian Zhou; [2023]
   Nyckelord :Small Target Detection; Target Tracking; YOLOv5; DeepSORT; Attention Mechanism; Loss Function; Feature Extraction and Fusion Network; Detektering Av små sål; sålspårning; YOLOv5; DeepSORT; uppmärksamhetsmekanism; förlustfunktion; fusionsnätverk;

   Sammanfattning : As an important indicator of biodiversity and ecological environment in a region, the number and distribution of animals has been given more and more attention by agencies such as nature reserves, wetland parks, and animal protection supervision departments. To protect biodiversity, we need to be able to detect and track the movement of animals to understand which animals are visiting the space. LÄS MER

4. 3. Efficient Sentiment Analysis and Topic Modeling in NLP using Knowledge Distillation and Transfer Learning

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

   Författare :George Malki; [2023]
   Nyckelord :Large Language Model; RoBERTa; Knowledge distillation; Transfer learning; Sentiment analysis; Topic modeling; Stor språkmodell; RoBERTa; Kunskapsdestillation; överföringsinlärning; Sentimentanalys; Ämnesmodellering;

   Sammanfattning : This abstract presents a study in which knowledge distillation techniques were applied to a Large Language Model (LLM) to create smaller, more efficient models without sacrificing performance. Three configurations of the RoBERTa model were selected as ”student” models to gain knowledge from a pre-trained ”teacher” model. LÄS MER

5. 4. Deep Ring Artifact Reduction in Photon-Counting CT

   Master-uppsats, KTH/Fysik

   Författare :Konstantinos Liappis; [2022]
   Nyckelord :Photon¬counting; Spectral CT; Material Decomposition; Deep learning; Resnet; Ring artifact; Sinogram; Fotonräknande; Spektral datortomografi; Materialdekomposition; Djupinlärning; Resnet; Ringartefakt; Sinogram;

   Sammanfattning : Ring artifacts are a common problem with the use of photon-counting detectors and commercial deployment rests on being able to compensate for them. Deep learning has been proposed as a candidate for tackling the inefficiency or high cost of traditional techniques. LÄS MER

7. 5. Deep Neural Networks for dictionary-based 5G channel estimation with no ground truth in mixed SNR scenarios

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

   Författare :Matteo Ferrini; [2022]
   Nyckelord :5G; Channel Estimation; Sparse Linear Inverse Problem; Approximate Message Passing; Neural Networks; 5G; kanaluppskattning; sparsamt linjärt inversproblem; approximativ meddelandeöverföring; neurala nätverk;

   Sammanfattning : Channel estimation is a fundamental task for exploiting the advantages of massive Multiple-Input Multiple-Output (MIMO) systems in fifth generation (5G) wireless technology. Channel estimates require solving sparse linear inverse problems that is usually performed with the Least Squares method, which brings low complexity but high mean squared error values. LÄS MER