Sökning: "generative models"

Visar resultat 1 - 5 av 62 avhandlingar innehållade orden generative models.

1. 1. Sampling from molecular unnormalized distributions with Deep Generative Models

   Författare :Juan Viguera Diez; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; machine learning; Cheminformatics; conformational sampling; generative models; drug discovery; Boltzmann generators;

   Sammanfattning : This thesis investigates how Deep Generative Models (DGMs) can address important drug discovery problems involving sampling from unnormalized distributions. It consists of two papers focusing on this challenge’s aspects: molecular design and conformational sampling. LÄS MER

3. 2. Probabilistic Sequence Models with Speech and Language Applications

   Författare :Gustav Eje Henter; W. Bastiaan Kleijn; Arne Leijon; Gernot Kubin; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Time series; acoustic modelling; speech synthesis; stochastic processes; causal-state splitting reconstruction; robust causal states; pattern discovery; Markov models; HMMs; nonparametric models; Gaussian processes; Gaussian process dynamical models; nonlinear Kalman filters; information theory; minimum entropy rate simplification; kernel density estimation; time-series bootstrap;

   Sammanfattning : Series data, sequences of measured values, are ubiquitous. Whenever observations are made along a path in space or time, a data sequence results. To comprehend nature and shape it to our will, or to make informed decisions based on what we know, we need methods to make sense of such data. LÄS MER

4. 3. Statistical inference with deep latent variable models

   Författare :Najmeh Abiri; Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Deep Learning; Generative Models; Variational Inference; Missing data; Imputation; Fysicumarkivet A:2019:Abiri;

   Sammanfattning : Finding a suitable way to represent information in a dataset is one of the fundamental problems in Artificial Intelligence. With limited labeled information, unsupervised learning algorithms help to discover useful representations. LÄS MER

5. 4. Generative models of limit order books

   Författare :Hanna Hultin; Henrik Hult; Erik Lindström; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Matematik; Mathematics;

   Sammanfattning : In this thesis generative models in machine learning are developed with the overall aim to improve methods for algorithmic trading on high-frequency electronic exchanges based on limit order books. The thesis consists of two papers. LÄS MER

7. 5. Generative Design Exploration : Computation and Material Practice

   Författare :Mania Aghaei Meibodi; Oliver Tessmann; Jonas Runberger; Neil Leach; KTH; []
   Nyckelord :HUMANIORA; HUMANITIES; Arkitektur; Architecture;

   Sammanfattning : Today, computation serves as an important intermediary agent for the integration of analyses and the constraints of materialisation into design processes. Research efforts in the field have emphasised digital continuity and conformity between different aspects of a building project. LÄS MER