Learning Under Concept Drift
thesis
posted on 2021-05-13, 05:56 authored by CHAITANYA MANAPRAGADAMost extant machine learning strategies focus on learning to make predictions in environments that assume concepts never change. This thesis studies how algorithms can make effective predictions in a changing world where processes of interest are constantly evolving.
History
Campus location
AustraliaPrincipal supervisor
Geoff Ian WebbAdditional supervisor 1
Mahsa SalehiYear of Award
2021Department, School or Centre
Information Technology (Monash University Clayton)Course
Doctor of PhilosophyDegree Type
DOCTORATEFaculty
Faculty of Information TechnologyUsage metrics
Categories
- Knowledge representation and reasoning
- Theory of computation not elsewhere classified
- Applied computing not elsewhere classified
- Artificial intelligence not elsewhere classified
- Pattern recognition
- Data mining and knowledge discovery
- Information systems not elsewhere classified
- Computational complexity and computability
Keywords
Online LearningStream LearningLearning under Concept DriftReal-time LearningMachine LearningData MiningOnline Machine LearningKnowledge Representation and Machine LearningTheoretical Computer ScienceApplied Computer ScienceArtificial Intelligence and Image ProcessingPattern Recognition and Data MiningInformation SystemsAnalysis of Algorithms and Complexity
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC