Sökning: L773:2192 6352 OR L773:2192 6360 >
The space of models...
The space of models in machine learning : using Markov chains to model transitions
-
- Torra, Vicenç (författare)
- Umeå universitet,Högskolan i Skövde,Institutionen för informationsteknologi,Forskningsmiljön Informationsteknologi,Department Computing Science, Umeå University, Sweden ; Hamilton Institute, Maynooth University, Ireland,Skövde Artificial Intelligence Lab (SAIL),Institutionen för datavetenskap,Hamilton Institute, Maynooth University, Maynooth, Ireland; School of Informatics, University of Skövde, Skövde, Sweden
-
- Taha, Mariam (författare)
- Umeå universitet,Institutionen för datavetenskap,Department Computing Science, Umeå University, Sweden
-
- Navarro-Arribas, Guillermo (författare)
- Dept. Information and Communications Engineering – CYBERCAT, Universitat Autònoma de Barcelona, Bellaterra, Catalonia, Spain
-
(creator_code:org_t)
- 2021-04-12
- 2021
- Engelska.
-
Ingår i: Progress in Artificial Intelligence. - : Springer. - 2192-6352 .- 2192-6360. ; 10:3, s. 321-332
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://his.diva-por... (primary) (Raw object)
-
https://link.springe...
-
https://umu.diva-por... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Machine and statistical learning is about constructing models from data. Data is usually understood as a set of records, a database. Nevertheless, databases are not static but change over time. We can understand this as follows: there is a space of possible databases and a database during its lifetime transits this space. Therefore, we may consider transitions between databases, and the database space. NoSQL databases also fit with this representation. In addition, when we learn models from databases, we can also consider the space of models. Naturally, there are relationships between the space of data and the space of models. Any transition in the space of data may correspond to a transition in the space of models. We argue that a better understanding of the space of data and the space of models, as well as the relationships between these two spaces is basic for machine and statistical learning. The relationship between these two spaces can be exploited in several contexts as, e.g., in model selection and data privacy. We consider that this relationship between spaces is also fundamental to understand generalization and overfitting. In this paper, we develop these ideas. Then, we consider a distance on the space of models based on a distance on the space of data. More particularly, we consider distance distribution functions and probabilistic metric spaces on the space of data and the space of models. Our modelization of changes in databases is based on Markov chains and transition matrices. This modelization is used in the definition of distances. We provide examples of our definitions.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Hypothesis space
- Machine and statistical learning models
- Probabilistic metric spaces
- Space of data
- Space of models
- Data privacy
- Distribution functions
- Machine learning
- Markov chains
- Constructing models
- Distance distribution functions
- Model Selection
- Model transition
- Nosql database
- Statistical learning
- Transition matrices
- Database systems
- Skövde Artificial Intelligence Lab (SAIL)
- Skövde Artificial Intelligence Lab (SAIL)
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas