Sökning: "acyclic"
Visar resultat 16 - 20 av 37 uppsatser innehållade ordet acyclic.
16. Dynamic Programming Algorithms for Semantic Dependency Parsing
Master-uppsats, Linköpings universitet/Interaktiva och kognitiva systemSammanfattning : Dependency parsing can be a useful tool to allow computers to parse text. In 2015, Kuhlmann and Jonsson proposed a logical deduction system that parsed to non-crossing dependency graphs with an asymptotic time complexity of O(n3), where “n” is the length of the sentence to parse. LÄS MER
17. Analysis of task scheduling for multi-coreembedded systems
Master-uppsats, KTH/Maskinkonstruktion (Inst.)Sammanfattning : This thesis performs a research on scheduling algorithms for parallel applications. The main focus is their usage on multi-core embedded systems’ applications. A parallel application can be described by a directed acyclic graph. LÄS MER
18. Generation of Abstract Meaning Representations by Hyperedge Replacement Grammars – A Case Study
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : The abstract meaning representation (AMR) is a graph-based semantic representation of a natural language sentence that has been the target of numerous studies – in particular, a collection of such graphs over a small domain including the words boy, girl, want and believe has been presented. We investigate the suitability of two hyperedge replacement grammar based formalisms for the generation of AMRs in the form of a case study using the aforementioned boy-girl domain. LÄS MER
19. Approximate Bayesian Learning of Partition Directed Acyclic Graphs
Master-uppsats, KTH/Matematisk statistikSammanfattning : Partition directed acyclic graphs (PDAGs) is a model whereby the conditional probability tables (CPTs) are partitioned into parts with equal probability. In this way, the number of parameters that need to be learned can be significantly reduced so that some problems become more computationally feasible. LÄS MER
20. Deep Learning with a DAG Structure for Segmentation and Classification of Prostate Cancer
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Deep learning is a machine learning technique inspired by the biological nervous system. The method has been used more and more over the last decades. Within this thesis, convolutional neural networks (CNN:s) are used for Gleason classification of prostate cancer in histopathological images. LÄS MER