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 14 of 14 for “"Structured Objects"”.
-
Use of prior knowledge in classification of similar and structured objects
… the examples, which is often true for real world objects. This does not mean lack of information for classification in the examples. On the contrary, there is still a clear pattern in the examples, but hidden behind a many-way covariance structure such that useful information is too dilute for …
-
Approximation algorithms for grammar-based data compression
… of approximation algorithms to hierarchically-structured objects. In this thesis, we establish hardness results, evaluate several previously proposed algorithms, and then present new procedures with much stronger approximation guarantees.
-
Efficient Similarity Search in Structured Data
… tasks in this area are the grouping of data objects (clustering), the classification of new data objects or the detection of exceptional data objects (outlier detection). Most algorithms for solving those problems are based on similarity search in databases. This makes efficient similarity …
-
Learning hypertrees with shortest path queries
… focuses on algorithms for learning discrete structured objects from queries. In this context, we consider the problem of learning a labeled hypergraph from a given family of hypergraphs using shortest path (SP) queries. An SP query specifies two vertices and asks for their distance in the …
-
Building Transparent Models
… with a black-box predictor, possibly over structured objects, and (iii) local certificates of robustness, derived for ensembles of any black-box predictors in continuous or discrete spaces. The contributions of this thesis are mainly methodological and theoretical. We also emphasize …
-
Molecular Graph Representation Learning and Generation for Drug Discovery
… new tools to apply these models to graph-structured objects. Moving away from the traditional graph neural network paradigm, we demonstrate the efficacy of prototype networks for molecular representation, which allows us to reason over learned property prototypes of molecules. Lastly, we …
-
A Classification Approach for Automated Reasoning Systems--A Case Study in Graph Theory
… systems which create classifications of structured objects face the problem of how object descriptions can be used to reflect their components as well as relations among these components. Current reasoning systems on graph theory do not adequately provide models to discover complex …
-
Modeling Intelligence via Graph Neural Networks
… be seeking statistical patterns in complex and structured objects, such as drug molecules and the global financial system. Advances in deep learning have shown that the key to solving such tasks is to learn a good representation. Given the representations of the world, the second aspect of …
-
Enhancement of the Fynbos Leaf Optical Recognition Application (FLORA-E)
… when attempting to classify irregular structured objects with high variability, such as stems and leafy stems. A redesign of the classification algorithms in the latest version, FLORA-E, was therefore necessary to cater for irregular fynbos stems. Numerous algorithms and techniques are …
-
Materials and processes for the optical additive manufacturing of advanced organic/inorganic nanocomposites for the mask-less plating of insulator and semiconductor substrates, and microfluidic devices
… The AM technologies allow to build 3D objects with complex geometries by adding layer-upon-layer of material without any mold and permits to fabricate structured objects and microfluidic systems with particular optical and mechanical properties which cannot be easily made with classical …
-
Generative models meet similarity search: efficient, heuristic-free and robust retrieval
… robustness. Finally, in domains with structured data such as graphs, we show that the computational methods in generative modeling have an interesting utility beyond estimating the data distribution and describe a retrieval framework that can explain its decision by borrowing the …
-
GPS-LiDAR sensor fusion aided by 3D city models for UAVs
… in urban areas, we expect the LiDAR to detect structured objects, such as buildings, which are primarily composed of surfaces and edges. Thus, we develop an efficient way for modelling the error covariance in the estimated incremental position based on each surface and edge feature point in the …
-
Coactive Learning Algorithms for Constructive Preference Elicitation
… elicitation framework is based on online structured prediction, a machine learning technique that deals with sequential decision problems over structured objects. By combining online structured prediction and state-of-the-art constraint solvers we can efficiently learn user utility models …