Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 17 of 17 for “"Probabilistic generative models"”.
-
Learning Probabilistic Generative Models For Fast Sampling-Based Planning
… We present several new learning approaches using probabilistic generative models for fast sampling-based planning. First, we propose fast collision detection in high dimensional configuration spaces based on Gaussian Mixture Models (GMMs) for Rapidly-exploring Random Trees (RRT). In addition, we …
-
Bayesian Computation and Optimal Decision Making in Primate Brains
… the nervous system may maintain internal probabilistic generative models for what caused its sensory input. In this dissertation, we examine many aspects of primate perceptual and motor behaviors and model them under the framework of Bayesian inference and optimality principle.
-
Wavelet Flow: Fast Training of High Resolution Normalizing Flows
Normalizing flows are a class of probabilistic generative models which allow for fast density computation, efficient sampling, and are effective at modelling complex distributions like images. A drawback among current methods is their significant training cost, sometimes requiring months of GPU …
-
Καινοτόμες μεθοδολογίες μηχανικής μαθήσεως
… clustering alternatives) for the treatment of probabilistic generative models. Furthermore, this work provided a novel hidden Markov model, offering significant benefits comparing to modem sequential data modeling techniques, as well as a new speaker verification methodology, based on Gaussian …
-
Visualisation of structured data through generative probabilistic modeling
… of topographic maps of structured data. A probabilistic generative model-based approach is taken, inspired by the GTM algorithm. De- pending on the data at hand, the form of a probabilistic generative model is specified that is appropriate for modelling the probability density of the data. …
-
Physics-Inspired Generative Deep Learning with Application to RNA Structure Prediction
… structures. This thesis develops a probabilistic generative modeling framework for learning such ensembles from limited molecular data. The central premise is that generative models are most effective for molecular science when physical inductive biases are included. The thesis …
-
Logical factorisation machines: probabilistic boolean factor models for binary data
… Machines (LFMs) are a class of latent feature models, that aim to decompose binary matrices, tensors or higher-arity relations into an approximate logical product of low rank, binary matrices. These products are defined through the use of logical operators instead of arithmetic operations. The …
-
Grounding and Generating 4D Humans in the Open World
… constraints. Second, they must be governed by probabilistic generative models that capture the manifold of human dynamics, enabling us to resolve ambiguity and synthesize plausible human behaviors. We realize this framework through a series of methods that progressively convert monocular videos …
-
Numerical Methods in Deep Learning and Computer Vision
… between disentanglement and orthogonality -- the generative models are enforced with different proposed orthogonality to show that the disentanglement performance is indeed improved. We also challenge the linear assumption of the latent traversal paths and propose to model the traversal process as …
-
New approaches to automated annotation of pathology-level findings in medical images
… and reliable segmentation, we propose to use probabilistic generative models, since they support the integration of expert knowledge and effectively handle the uncertainties inherent in the images and segmentation. However, when a priori knowledge is not available, these generative models are …
-
Distributed Representations of Topics
… modeling are Latent Dirichlet Allocation and Probabilistic Latent Semantic Analysis. They are probabilistic generative models and, despite their popularity, they have several weaknesses. In order to achieve optimal results, they often require the number of topics to be known. They need custom …
-
Privacy-preserving seedbased data synthesis
… data records by conditioning the output of a generative model on some input data record called the seed. This technique produces synthetic records that are similar to their seeds, which results in high quality outputs. But it simultaneously introduces statistical dependence between synthetic …
-
Community-Oriented Models and Applications for the Social Web
… • First, we propose a pair of novel probabilistic generative models for describing and modeling community-oriented social bookmarking. We show how these models enable effective extraction of meaningful communities over large real world social bookmarking services. • Second, we develop …
-
Machine Learning Methods for Microarray Data Analysis
… and their locations within the cell. Novel probabilistic generative models are proposed for clustering genes using both their expression levels and GO tags. These models are similar in essence to the ones used for multimodal data, such as images and words, with learning and inference done in …
-
Deep generative model for synthesising and analysing cardiac magnetic resonance images
… and provide variable results. At the same time, generative models have advanced medical image analysis, especially for downstream cardiac image analysis tasks. The aim is to use these synthetic images as viable alternatives to real data in deep learning model training, providing cutting-edge …
-
Grounded language learning models for ambiguous supervision
… In this thesis, we focus on devising effective models for simultaneously disambiguating such supervision and learning the underlying semantics of language to map NL sentences into proper logical MRs. We present probabilistic generative models for learning such correspondences along with a …
-
Demonstrační aplikace lineární logistické regrese
Táto bakalárska práca sa zaoberá lineárnou logistickou regresiou, modelom pre strojové učenie. Cieľom tejto práce je podrobne preskúmať a zanalyzovať ako tento klasifikačný model funguje, aby bolo možné vyvinúť učebnú pomôcku vo forme demonštračnej aplikácie. Všetky matematické rovnice, logistická …