Spelling suggestions: "subject:"anda achine 1earning"" "subject:"anda achine _learning""
161 |
Feasibility of using network support data to predict risk level of trouble ticketsLaurentz, Henrik January 2016 (has links)
Internet Service Providers gather vast amounts of data in the form of trouble tickets created from connectivity related issues. This data is often stored and seldom used for proactive purposes. This thesis explores the feasibility of finding correlations in network support data through the use of data mining activities. Correlations such as these could be used for improving troubleshooting or staffing related activities. The approach uses the data mining methodology CRISP-DM to investigate typical data mining operations from the perspective of a Network Operation Center. The results show that correlations between the solving time and other ticket related attributes do exist and that support data could be used for the activities mentioned. The results also show that it exists a lot of room for improvement when it comes to data mining activities in network support data.
|
162 |
Dynamic planning and scheduling in manufacturing systems with machine learning approachesYang, Donghai., 杨东海. January 2008 (has links)
published_or_final_version / Industrial and Manufacturing Systems Engineering / Doctoral / Doctor of Philosophy
|
163 |
Latent variable models of distributional lexical semanticsReisinger, Joseph Simon 24 October 2014 (has links)
Computer Sciences / In order to respond to increasing demand for natural language interfaces---and provide meaningful insight into user query intent---fast, scalable lexical semantic models with flexible representations are needed. Human concept organization is a rich phenomenon that has yet to be accounted for by a single coherent psychological framework: Concept generalization is captured by a mixture of prototype and exemplar models, and local taxonomic information is available through multiple overlapping organizational systems. Previous work in computational linguistics on extracting lexical semantic information from unannotated corpora does not provide adequate representational flexibility and hence fails to capture the full extent of human conceptual knowledge. In this thesis I outline a family of probabilistic models capable of capturing important aspects of the rich organizational structure found in human language that can predict contextual variation, selectional preference and feature-saliency norms to a much higher degree of accuracy than previous approaches. These models account for cross-cutting structure of concept organization---i.e. selective attention, or the notion that humans make use of different categorization systems for different kinds of generalization tasks---and can be applied to Web-scale corpora. Using these models, natural language systems will be able to infer a more comprehensive semantic relations, which in turn may yield improved systems for question answering, text classification, machine translation, and information retrieval. / text
|
164 |
Cartesian granule features : knowledge discovery for classification and predictionShanahan, James Gerard January 1998 (has links)
No description available.
|
165 |
Application of sequence prediction to data compressionChung, Jimmy Hok Leung January 2000 (has links)
No description available.
|
166 |
Generating artificial data for the evaluation of concept learning algorithmsHunniford, Thomas J. C. January 1998 (has links)
No description available.
|
167 |
Learning Bayesian networks from data : an information theory based approachCheng, Jie January 1998 (has links)
No description available.
|
168 |
Towards a unified framework of relevanceWang, Hui January 1996 (has links)
No description available.
|
169 |
A neural network based search heuristic and its application to computer chessGreer, Kieran R. C. January 1998 (has links)
No description available.
|
170 |
Introspective techniques for maintaining retrieval knowledge in case-base reasoningPatterson, William Robert David January 2001 (has links)
No description available.
|
Page generated in 0.0781 seconds