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 8 of 8 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 …
-
Infrastructure for modeling and inference engineering with 3D generative scene graphs
Recent advances in probabilistic programming have enabled the development of probabilistic generative models for visual perception using a rich abstract representation of 3D scene geometry called a scene graph. However, there remain several challenges in the practical implementation of scene graph …
-
Natively probabilistic computation
I introduce a new set of natively probabilistic computing abstractions, including probabilistic generalizations of Boolean circuits, backtracking search and pure Lisp. I show how these tools let one compactly specify probabilistic generative models, generalize and parallelize widely used sampling …
-
Venture : an extensible platform for probabilistic meta-programming
… describes Venture, an extensible platform for probabilistic meta-programming. In Venture, probabilistic generative models, probability density functions, and probabilistic inference algorithms are all first-class objects. Any Venture program that makes random choices can be treated as a …
-
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 …
-
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 …
-
Anomalous Inputs in Deep Learning: a Probabilistic Perspective
… sets of tools. In this thesis I introduce a probabilistic framework that I call the `three distribution problem', which unifies both tasks. I use this framework to develop new methods for detecting OOD inputs and for creating adversarial attacks. Furthermore, my three-distribution approach …
-
Image Compression using Sum-Product Networks
… a data independent encoder, and it employs a probabilistic graphical model (PGM) to model the source structure in the decoder. Decoding is performed by running belief propagation over the graphical models representing the modeling and coding aspects of compression. In practical settings where …