Sökning: "Network inference"

Visar resultat 1 - 5 av 136 uppsatser innehållade orden Network inference.

1. 1. Exploring the Depth-Performance Trade-Off : Applying Torch Pruning to YOLOv8 Models for Semantic Segmentation Tasks

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

   Författare :Xinchen Wang; [2024]
   Nyckelord :Deep Learning; Semantic segmentation; Network optimization; Network pruning; Torch Pruning; YOLOv8; Network Depth; Djup lärning; Semantisk segmentering; Nätverksoptimering; Nätverksbeskärning; Fackelbeskärning; YOLOv8; Nätverksdjup;

   Sammanfattning : In order to comprehend the environments from different aspects, a large variety of computer vision methods are developed to detect objects, classify objects or even segment them semantically. Semantic segmentation is growing in significance due to its broad applications in fields such as robotics, environmental understanding for virtual or augmented reality, and autonomous driving. LÄS MER

3. 2. Uncertainty Estimation in Radiation Dose Prediction U-Net

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

   Författare :Frida Skarf; [2023]
   Nyckelord :Radiation dose prediction models; U-net; quantile regression; Monte Carlo Dropout; epistemic uncertainty estimation; aleatoric uncertainty estimation; Stråldospredicerande modeller; U-net; kvantilregression; Monte Carlo Dropout; epistemisk osäkerhetsskattning; aletorisk osäkerhetsskattning;

   Sammanfattning : The ability to quantify uncertainties associated with neural network predictions is crucial when they are relied upon in decision-making processes, especially in safety-critical applications like radiation therapy. In this paper, a single-model estimator of both epistemic and aleatoric uncertainties in a regression 3D U-net used for radiation dose prediction is presented. LÄS MER

4. 3. Object Recognition in Satellite imagesusing improved ConvolutionalRecurrent Neural Network

   Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

   Författare :TARUN NATTALA; [2023]
   Nyckelord :CRNN; CNN; RNN; Machine Learning and Satellite Image Recognition.;

   Sammanfattning : Background:The background of this research lies in detecting the images from satellites. The recognition of images from satellites has become increasingly importantdue to the vast amount of data that can be obtained from satellites. This thesisaims to develop a method for the recognition of images from satellites using machinelearning techniques. LÄS MER

5. 4. Parameter Inference for Stochastic Models of Gene Expression in Eukaryotic Cells

   Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Ansar Siddiqui; [2023]
   Nyckelord :;

   Sammanfattning : Simulation models are often used to study a system or phenomenon. However, before a simulation model can be used, its parameter needs to be fit to mimic observed data. This is called the parameter inference problem. LÄS MER

7. 5. Deep Learning Model Deployment for Spaceborne Reconfigurable Hardware : A flexible acceleration approach

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

   Författare :Javier Ferre Martin; [2023]
   Nyckelord :Space Situational Awareness; Deep Learning; Convolutional Neural Networks; FieldProgrammable Gate Arrays; System-On-Chip; Computer Vision; Dynamic Partial Reconfiguration; High-Level Synthesis; Rymdsituationstänksamhet; Djupinlärning; Konvolutionsnätverk; Omkonfigurerbara Field-Programmable Gate Arrays FPGAs ; System-On-Chip SoC ; Datorseende; Dynamisk partiell omkonfigurering; Högnivåsyntes.;

   Sammanfattning : Space debris and space situational awareness (SSA) have become growing concerns for national security and the sustainability of space operations, where timely detection and tracking of space objects is critical in preventing collision events. Traditional computer-vision algorithms have been used extensively to solve detection and tracking problems in flight, but recently deep learning approaches have seen widespread adoption in non-space related applications for their high accuracy. LÄS MER