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 6 of 6 for “"relational inference"”.
-
Lifted probabilistic relational inference for uncertain networks
Probabilistic Relational Graphical Model (PRGM) is a popular tool for modeling uncertain relational knowledge, of which the set of uncertain relational knowledge is usually assumed to be independent with the domain of the application. One common application of PRGM is to model complex networks …
-
On machine learning methods for time series with financial applications
… shift. The third project, “Rethinking Neural Relational Inference for Granger Causal Discovery”, studies the limitations of Neural Relational Inference, which is a graph-based variational auto-encoder model, in recovering the Granger Causal structure of multivariate time series. While a …
-
Looking for Meaning: Autistic Traits and Attention to Sincerity in Social Exchange
… movements were recorded. The videos, from the Relational Inference in Social Communication dataset (Rothermich & Pell, 2015), depicted everyday social interactions that varied in sincerity (literal vs. joking vs. sarcastic) and intention (positive vs. negative). Participants were divided into …
-
Visualization of logic programming
… we examine a logic programming language, Fuzzy Relational Inference Language (Fril), and discuss the development and operation of the Fril Visual Tracer (FVT), a program designed to graphically present Fril's execution process to the user. A discussion of the FVT is preceded by an overview of …
-
Accelerating Graph Networks for Real-Time Physics Simulation
… dimensionality of the dataset means that the inference happens on a very large graph and rollouts do not occur in real-time. To accelerate the simulation, Haeri and Skonieczny (2021) developed a method that uses dimensionality reduction techniques such as principal component analysis (PCA). …
-
Data and Computation-efficient Deep Learning for Multi-agent Systems
The primary goal of this research is to build data and computation-efficient deep learning methods for multi-agent systems. Multi-agent systems are present in a wide range of domains, from physical systems (e.g., molecules, planets) and biological systems (e.g., host-pathogen interactions, neurons) …