Collective Interpretation and Potential Joint Information Maximization

Abstract : The present paper aims to propose a new type of information-theoretic method called “potential joint information maximization”. The joint information maximization has an effect to reduce the number of jointly fired neurons and then to stabilize the production of final representations. Then, the final connection weights are collectively interpreted by averaging weights produced by different data sets. The method was applied to the data set of rebel participation among youths. The result show that final weights could be collectively interpreted and only one feature could be extracted. In addition, generalization performance could be improved.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01615007
Contributor : Hal Ifip <>
Submitted on : Wednesday, October 11, 2017 - 4:58:33 PM
Last modification on : Monday, December 3, 2018 - 3:44:13 PM
Long-term archiving on: Friday, January 12, 2018 - 3:26:46 PM

File

433802_1_En_2_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Ryotaro Kamimura. Collective Interpretation and Potential Joint Information Maximization. 9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. pp.12-21, ⟨10.1007/978-3-319-48390-0_2⟩. ⟨hal-01615007⟩

Share

Metrics

Record views

264

Files downloads

117