TY - JOUR
T1 - Investigation of Incremental Learning as Temporal Feature Extraction
AU - Matsumori, Shoya
AU - Abe, Yuki
AU - Osawa, Masahiko
AU - Imai, Michita
N1 - Funding Information:
a Keio University Graduated School of Science for Open and Environmental Systems, a Keio University Graduated School of Science for Open and Environmental Systems, 3-14-1 Hiyoshbi, Kohoku-ku, Yokohama, Kanagawa Prefecture, 223-8522, Japan 3-14-1Hiyoshi,b KKeioohUniveroku-ku,sityYokFohama,aculty ofKanaSciencegawaandPreTfeeccthnoloure, 223-8522,gy, Japan c 3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa Prefecture, 223-8522, Japan c Japan Society for the Promotion of Science, Research Fellow (DC1) Tokyo, Japan
Publisher Copyright:
© 2018 The Authors. Published by Elsevier B.V.
PY - 2018
Y1 - 2018
N2 - 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).
AB - 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).
KW - incremental learning restricted boltzmann machine
KW - slow feature analysis
KW - time series analysis
UR - http://www.scopus.com/inward/record.url?scp=85059476753&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059476753&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2018.11.082
DO - 10.1016/j.procs.2018.11.082
M3 - Conference article
AN - SCOPUS:85059476753
SN - 1877-0509
VL - 145
SP - 342
EP - 347
JO - Procedia Computer Science
JF - Procedia Computer Science
T2 - 9th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2018
Y2 - 22 August 2018 through 24 August 2018
ER -