Sökning: "Alternative architectures"
Visar resultat 1 - 5 av 53 uppsatser innehållade orden Alternative architectures.
1. Virtual H&E Staining Using PLS Microscopy and Neural Networks
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Histopathological examination, crucial in diagnosing diseases such as cancer, traditionally relies on time- and resource-consuming, poorly standardized chemical staining for tissue visualization. This thesis presents a novel digital alternative using generative neural networks and a point light source (PLS) microscope to transform unstained skin tissue images into their stained counterparts. LÄS MER
2. Estimating Diffusion Tensor Distributions With Neural Networks
Master-uppsats, Linköpings universitet/Algebra, geometri och diskret matematik; Linköpings universitet/Tekniska fakultetenSammanfattning : Magnetic Resonance Imaging (MRI) is an essential healthcare technology, with diffusion MRI being a specialized technique. Diffusion MRI exploits the inherent diffusion of water molecules within the human body to produce a high-resolution tissue image. An MRI image contains information about a 3D volume in space, composed of 3D units called voxels. LÄS MER
3. Anomaly Detection inCombustion Engines withSound Recognition
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : As a global manufacturer of commercial vehicles, Scania is aiming for delivering high-quality products to its customers. Therefore, testing the produced components before assembling the final product and delivering it to the customer is key. LÄS MER
4. A Transformer-Based Scoring Approach for Startup Success Prediction : Utilizing Deep Learning Architectures and Multivariate Time Series Classification to Predict Successful Companies
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The Transformer, an attention-based deep learning architecture, has shown promising capabilities in both Natural Language Processing and Computer Vision. Recently, it has also been applied to time series classification, which has traditionally used statistical methods or the Gated Recurrent Unit (GRU). LÄS MER
5. Exploring Normalizing Flow Modifications for Improved Model Expressivity
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Normalizing flows represent a class of generative models that exhibit a number of attractive properties, but do not always achieve state-of-the-art performance when it comes to perceived naturalness of generated samples. To improve the quality of generated samples, this thesis examines methods to enhance the expressivity of discrete-time normalizing flow models and thus their ability to capture different aspects of the data. LÄS MER