Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (316kB) | Preview |
Algebraic representation of generative classifier
Citation
Varando, Gherardo and Riccomagno, Eva (2017). Algebraic representation of generative classifier. In: "First Italian Meeting on Probability and Mathematical Statistics", 19-22 Jun 2017, Turín. p. 1.
Description
| Title: | Algebraic representation of generative classifier |
|---|---|
| Author/s: |
|
| Item Type: | Presentation at Congress or Conference (Other) |
| Event Title: | First Italian Meeting on Probability and Mathematical Statistics |
| Event Dates: | 19-22 Jun 2017 |
| Event Location: | Turín |
| Title of Book: | First Italian Meeting on Probability and MathematicalStatisticsTorino, 19-22/6/2017: book of abstracts |
| Date: | 2017 |
| Subjects: | |
| Faculty: | E.T.S. de Ingenieros Informáticos (UPM) |
| Department: | Inteligencia Artificial |
| Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
Abstract
We study the discrimination functions associated with classifiers induced by probabilistic graphical models and in particular Bayesian network classifiers. For every G -Markov probabilistic classifier we link the topology of the graph G with the class of discrimination functions induced, we prove that every conditional independence statement satisfied by the model implies linear constrains on the discrimination function. As an example we study the Naive Bayes model for two binary predictor variables and we formulate some questions for future work.
Funding Projects
| Type | Code | Acronym | Leader | Title |
|---|---|---|---|---|
| Government of Spain | C080020-09 | Unspecified | Universidad Politécnica de Madrid | Cajal Blue Brain |
More information
| Item ID: | 51136 |
|---|---|
| DC Identifier: | https://oa.upm.es/51136/ |
| OAI Identifier: | oai:oa.upm.es:51136 |
| Official URL: | http://calvino.polito.it/~probstat/torino2017/index.html |
| Deposited by: | Memoria Investigacion |
| Deposited on: | 05 Feb 2019 10:06 |
| Last Modified: | 05 Feb 2019 10:06 |
