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 5 of 5 for “"Sum-Product networks"”.

  1. An Empirical Study on Sum-Product Networks Structure Learning and Deep Convolutional Sum-Product Networks

    Sum-product Networks (SPNs) are generative probabilistic models which obtained the attention of the community for its tractability and easy methods for learning. Our rst main contribution is an empirical comparison of methods for SPN learning and inference. LearnSPN is a popular algorithm for …

    regina Repository record for An Empirical Study on Sum-Product Networks Structure Learning and Deep Convolutional Sum-Product Networks (opens in a new tab)

  2. Image Compression using Sum-Product Networks

    … architecture based on recently proposed sum-product networks (SPNs), a class of tractable probabilistic generative models, to model the source distribution. Our architecture strikes a balance between efficient learning of source structure and fast lossless decoding. We show that SPNs …

    mit Repository record for Image Compression using Sum-Product Networks (opens in a new tab)

  3. Robustness in sum-product networks: from measurement to ensembles

    … the problem of trust in classifications using Sum-Product Networks. A method of gauging the reliability of a classification through perturbing model weights using Credal Sum-Product Networks and creating a metric in the form of robustness to represent this is presented and demonstrated …

    qu-belfast Repository record for Robustness in sum-product networks: from measurement to ensembles (opens in a new tab)

  4. The Sum-Product Theorem and its Applications

    … deep learning. I first identify and prove the sum-product theorem, which states that in any semiring for inference to be tractable it suffices that the factors of every product have disjoint scopes; i.e., that they are decomposable. I show that this simple condition unifies and extends many …

    washington Repository record for The Sum-Product Theorem and its Applications (opens in a new tab)

  5. New probabilistic approaches for detecting and evaluating concept drift in data streams

    … of SPNCD, a probabilistic method leveraging Sum-Product Networks (SPNs) to detect real and virtual drifts by analyzing shifts in the joint probability distribution of features and class labels. Inspired by the Bayesian CD definition, SPNCD integrates prediction error, which assesses model …

    regina Repository record for New probabilistic approaches for detecting and evaluating concept drift in data streams (opens in a new tab)