A Note on the Utility of Incremental Learning

Giraud-Carrier Christophe

Research output: Contribution to journalArticle (Academic Journal)peer-review

134 Citations (Scopus)


Historically, inductive machine learning has focused on non-incremental learning tasks, i.e., where the training set can be constructed a priori and learning stops once this set has been duly processed. There are, however, a number of areas, such as agents, where learning tasks are incremental. This paper defines the notion of incrementality for learning tasks and algorithms. It then provides some motivation for incremental learning and argues in favour of the design of incremental learning algorithms for solving incremental learning tasks. A number of issues raised by such systems are outlined and the incremental learner ILA is used for illustration.
Translated title of the contributionA Note on the Utility of Incremental Learning
Original languageEnglish
Article number215-223
Pages (from-to)215 - 233
JournalAI Communications
Volume13 (4)
Publication statusPublished - 2000

Bibliographical note

Other identifier: 1000535


Dive into the research topics of 'A Note on the Utility of Incremental Learning'. Together they form a unique fingerprint.

Cite this