Investigation of Incremental Learning as Temporal Feature Extraction | Zendy

Shoya Matsumori | Zendy; Yuki Abe | Zendy; Masahiko Osawa | Zendy; Michita Imai | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Investigation of Incremental Learning as Temporal Feature Extraction

Author(s) -

Shoya Matsumori,

Yuki Abe,

Masahiko Osawa,

Michita Imai

Publication year - 2018

Publication title -

procedia computer science

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.334

H-Index - 76

ISSN - 1877-0509

DOI - 10.1016/j.procs.2018.11.082

Subject(s) - mnist database , computer science , restricted boltzmann machine , artificial intelligence , feature learning , representation (politics) , feature (linguistics) , feature extraction , pattern recognition (psychology) , incremental learning , machine learning , boltzmann machine , extraction (chemistry) , deep learning , linguistics , philosophy , chemistry , chromatography , politics , political science , law

In this paper we discuss an effect of feature extraction using Incremental Learning Restricted Boltzmann Machine (IL-RBM). We trained the model on Moving MNIST and analyzed the obtained representation by visualizing hidden activities and reported some meaningful features obtained in incremental learning, similar to that of obtained in Slow Feature Analysis (SFA).

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research