Learning-based Programming Paradigm: Difference between revisions
Jump to navigation
Jump to search
m (Text replacement - "<P> [[" to "<P> [[") |
m (Text replacement - " [[" to " [[") |
||
| Line 9: | Line 9: | ||
=== 2011 === | === 2011 === | ||
* http://cogcomp.cs.illinois.edu/page/project_view/23 | * http://cogcomp.cs.illinois.edu/page/project_view/23 | ||
** [[Learning based program]]s are [[software application]]s that utilize [[machine learning technology]] to [[interact with]] | ** [[Learning based program]]s are [[software application]]s that utilize [[machine learning technology]] to [[interact with]] [[naturally occurring data]] that are highly [[variable data|variable]] and [[ambiguous|ambiguous data]]. They lend themselves towards a [[computational model]] in which some of the [[variable]]s, [[concept]]s, and [[relation]]s may be [[task definition task|defined]] only in a [[data-driven task|data driven way]], or may not be unambiguously defined without relying on other concepts acquired this way. Unfortunately, neither [[modern programming language]]s nor the [[mathematical abstraction]]s so cleanly utilized by [[machine learning researcher]]s facilitate such a [[programming model|model]]. As a result, it is inevitable that the design of systems with multiple learning components becomes quite complex, and their efficient implementation can only be accomplished by those with expertise both in the selected [[learning algorithm]]s and the application domain. Even when such expertise is available, implementations of conceptually simple learning-based programs can be time consuming and prone to error. <P> [[Learning-based Programming Paradigm|Learning Based Programming (LBP)]] is a [[programming paradigm]] that addresses these issues. In [[Learning-based Programming Paradigm|LBP]], the implementation details of feature extraction, learning, and inference are abstracted away from the [[programmer]] so that he or she may focus more directly on the design of his application. To accomplish this, an [[Learning-based Programming Paradigm|LBP]] implementation formalizes the definitions of these concepts so that they may be integrated into a [[programming language]], enabling the [[programmer]] to use them as building blocks. Using [[Learning-based Programming Paradigm|LBP]], a programmer names classifiers and optionally provides [[hard-coded definition]]s for them. Where [[hard-coded definition]]s are not available, other classifiers are designated as information sources, and the compiler takes care of learning the desired classifiers from data. Constraints over one or more classifiers' outputs may also be imposed declaratively, and [[learned classifier]]s will automatically respect them. | ||
=== 2010 === | === 2010 === | ||
Latest revision as of 09:04, 23 May 2024
A Learning-based Programming Paradigm is a Data-Driven Programming Paradigm that includes the ability to insert machine learning operations.
References
2011
- http://cogcomp.cs.illinois.edu/page/project_view/23
- Learning based programs are software applications that utilize machine learning technology to interact with naturally occurring data that are highly variable and ambiguous data. They lend themselves towards a computational model in which some of the variables, concepts, and relations may be defined only in a data driven way, or may not be unambiguously defined without relying on other concepts acquired this way. Unfortunately, neither modern programming languages nor the mathematical abstractions so cleanly utilized by machine learning researchers facilitate such a model. As a result, it is inevitable that the design of systems with multiple learning components becomes quite complex, and their efficient implementation can only be accomplished by those with expertise both in the selected learning algorithms and the application domain. Even when such expertise is available, implementations of conceptually simple learning-based programs can be time consuming and prone to error.
Learning Based Programming (LBP) is a programming paradigm that addresses these issues. In LBP, the implementation details of feature extraction, learning, and inference are abstracted away from the programmer so that he or she may focus more directly on the design of his application. To accomplish this, an LBP implementation formalizes the definitions of these concepts so that they may be integrated into a programming language, enabling the programmer to use them as building blocks. Using LBP, a programmer names classifiers and optionally provides hard-coded definitions for them. Where hard-coded definitions are not available, other classifiers are designated as information sources, and the compiler takes care of learning the desired classifiers from data. Constraints over one or more classifiers' outputs may also be imposed declaratively, and learned classifiers will automatically respect them.
- Learning based programs are software applications that utilize machine learning technology to interact with naturally occurring data that are highly variable and ambiguous data. They lend themselves towards a computational model in which some of the variables, concepts, and relations may be defined only in a data driven way, or may not be unambiguously defined without relying on other concepts acquired this way. Unfortunately, neither modern programming languages nor the mathematical abstractions so cleanly utilized by machine learning researchers facilitate such a model. As a result, it is inevitable that the design of systems with multiple learning components becomes quite complex, and their efficient implementation can only be accomplished by those with expertise both in the selected learning algorithms and the application domain. Even when such expertise is available, implementations of conceptually simple learning-based programs can be time consuming and prone to error.
2010
- (Rizzolo & Roth, 2010) ⇒ Nick Rizzolo, and Dan Roth. (2010). “Learning Based Java for Rapid Development of NLP Systems.” In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2010).