Sökning: "Konstgjorda neurala nätverk"
Hittade 5 uppsatser innehållade orden Konstgjorda neurala nätverk.
1. Monocular 3D Human Pose Estimation
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The focus of this work is the task of 3D human pose estimation, more specifically by making use of key points located in single monocular images in order to estimate the location of human body joints in a 3D space. It was done in association with Tracab, a company based in Stockholm, who specialises in advanced sports tracking and analytics solutions. LÄS MER
2. Basil-GAN
Master-uppsats, KTH/Matematisk statistikSammanfattning : Developments in computer vision has sought to design deep neural networks which trained on a large set of images are able to generate high quality artificial images which share semantic qualities with the original image set. A pivotal shift was made with the introduction of the generative adversarial network (GAN) by Goodfellow et al.. LÄS MER
3. Investigating the Spectral Bias in Neural Networks
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : Neural networks have been shown to have astounding performance on a variety of different machine learning tasks and data sets, both for synthetic and real-world data.However, in spite of their widespread usage and implementation, the convergence and the training dynamics of neural networks are neither trivial, nor completely understood. LÄS MER
4. Unsupervised learning of data representations in brain-like neural networks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Recently, there has been a growing interest in brain-plausible neural networks that closely resemble the brain’s structure. However, conventional networks do not make good models for the brain since these connections are modelled differently, hence the interest in brain-plausible networks. LÄS MER
5. Topological recursive fitting trees : A framework for interpretable regression extending decision trees
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Many real-world machine learning applications need interpretation of an algorithm output. The simplicity of some of the most fundamental machine learning algorithms for regression, such as linear regression or decision trees, facilitates interpretation. However, they fall short when facing complex (e.g. LÄS MER