Sökning: "Normaliserande Flöden"

Hittade 4 uppsatser innehållade orden Normaliserande Flöden.

1. 1. Exploring Normalizing Flow Modifications for Improved Model Expressivity

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

   Författare :Marcel Juschak; [2023]
   Nyckelord :Normalizing Flows; Motion Synthesis; Invertible Neural Networks; Glow; MoGlow; Maximum Likelihood Estimation; Generative models; normaliserande flöden; rörelsesyntes; inverterbara neurala nätverk; Glow; MoGlow; maximum likelihood-skattning generativa modeller;

   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

3. 2. Believable and Manipulable Facial Behaviour in a Robotic Platform using Normalizing Flows

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

   Författare :Kildo Alias; [2021]
   Nyckelord :Nonverbal Behaviour; Machine Learning; Generative Models; Normalizing Flows; Human-Robot Interaction; Icke-verbalt beteende; Maskininlärning; Generativa modeller; Normaliserande Flöden; Människa-robot interaktion.;

   Sammanfattning : Implicit communication is important in interaction because it plays a role in conveying the internal mental states of an individual. For example, emotional expressions that are shown through unintended facial gestures can communicate underlying affective states. LÄS MER

4. 3. Real-Time Probabilistic Locomotion Synthesis for Uneven Terrain

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

   Författare :Emil Jonsson; [2021]
   Nyckelord :Machine learning; Probabilistic models; Normalising flow; Environment interaction; Animation Synthesis; Maskinginlärning; Probabilistiska metoder; Normaliserande flöden; Interaktion med omgivning; Animations-syntes;

   Sammanfattning : In modern games and animation there is a constant strive for more realistic motion. Today a lot of games use motion matching and blending with lots of post-processing steps to produce animations, but these methods often require huge amounts of motions clips while still having problems with realistic joint weights. LÄS MER

5. 4. Neural Networks and Uncertainty Estimation for Financial Asset Predictions

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

   Författare :Robert Cedergren; [2020]
   Nyckelord :;

   Sammanfattning : With the capability of modeling complex non-linear mappings, neural networks have obtained state-of-the-art performance on various tasks. However, traditional neural networks are prone to overfitting as they tend to be overconfident on unseen, noisy and incorrectly labeled data. Neither do they produce meaningful representations of uncertainty. LÄS MER