# Mohon maaf, crossposting ke beberapa milis.
Assalamualaikum Wr Wb
Terlampir saya kirimkan pengantar dari colloquium ke-7 yang
berlangsung sejak hari ini di milis [EMAIL PROTECTED]
Colloquium ini adalah rangkaian kegiatan di milis [EMAIL PROTECTED]
yang bertujuan untuk mempercepat diseminasi informasi di
kalangan pemerhati, peneliti, peminat softcomputing dan
tema-tema yg terkait dengannya. Pada colloquium sebelumnya,
dipresentasikan sisi aplikasi dari softcomputing di bidang
gempa bumi, pertanian, industri parfum, medical engineering,
dsb. Pada kesempatan ini kolokium diisi dengan sisi teori,
yang berpotensi untuk diaplikasikan pada berbagai bidang.
1.Jadwal Kolokium (jadwal sementara ini baru sampai September 2006)
http://penguin.life.chukyo-u.ac.jp/~nugroho/jadwal.pdf
2.Aktifitas milis dapat diikuti resumenya dari
http://softcomputing.wordpress.com
3.Arsip colloquium, tutorial, koleksi data, dsb. dapat
ditengok di
http://penguin.life.chukyo-u.ac.jp/~nugroho/sc.html
(untuk download, silakan mendaftar terlebih dahulu sbg. anggota milis)
Sekiranya rekan-rekan berminat untuk mengikutinya,
dipersilakan untuk bergabung di milis, dengan mengirim
email ke [EMAIL PROTECTED] berisi :
- Nama
- Afiliasi
- Bidang yang diminati atau riset yang ditekuni
- lain-lain (bebas)
Wassalamualaikum Wr Wb
____________________________________________________________________________________________
Anto Satriyo Nugroho, Dr.Eng
E-mail : [EMAIL PROTECTED], [EMAIL PROTECTED]
URL : http://www.asnugroho.net/ Tel. +81-565-46-6638 Fax. +81-565-46-1299
- School of Life System Science & Technology, Chukyo University, Toyota-Japan
(Visiting Prof.)
- Agency for the Assessment and Application of Technology (BPPT),
Jakarta-Indonesia
*** Colloquium ke-7 milis softcomputing ***
Non-Linear Classification Using Ensemble of Linear Perceptrons
Penyaji : Pitoyo Hartono
Future University-Hakodate, Hakodate City, Japan
E-mail:[EMAIL PROTECTED]
Recently, several models of neural networks ensemble have
been proposed, generally with the objective of achieving
a higher generalization performance compared to the singular
neural network. Some of the ensembles, represented by Boosting
and Mixture of Experts, proposed mechanisms to divide the
learning space into a number of sub-spaces and assign each
sub-space into one of the ensemble's member, hence the learning
load of each member can be relaxed, leading to better
convergence and performance. In this paper, an ensemble of
linear perceptron (ELP) with an algorithm that effectively
divides the learning space in a linear manner, and assign the
classification task of each sub-space to a linear perceptron,
is proposed. The objective of this algorithm is to achieve a
linear decomposition of a nonlinear problem through an automatic
divide and conquer approach. In ELP, in addition to the ordinary
output neurons, each linear perceptron has an additional neuron
in its output layer. The additional neuron is called “confident
neuron”, and produces an output that indicates the “confidence
level” of the perceptron with regard to its ordinary output.
An output of the perceptron which has a high confidence level
can be considered as a reliable output, while an output with low
confidence level is an unreliable one. The proposed ELP is equipped
with a competitive mechanism for learning space division based
on the confidence levels and at the same time to train each member
to perform in the assigned sub learning space. The linearity of
each member also enables us to analyze the division of the problem
space that can be useful in understanding the structure of the
problems and also to analyze the overall performance of the ensemble.
--------------------------------------
Let's start Yahoo! Auction - Free Campaign Now!
http://pr.mail.yahoo.co.jp/auction/
------------------------ Yahoo! Groups Sponsor --------------------~-->
Get to your groups with one click. Know instantly when new email arrives
http://us.click.yahoo.com/.7bhrC/MGxNAA/yQLSAA/iq7wlB/TM
--------------------------------------------------------------------~->
Yahoo! Groups Links
<*> To visit your group on the web, go to:
http://groups.yahoo.com/group/dosen-peneliti/
<*> To unsubscribe from this group, send an email to:
[EMAIL PROTECTED]
<*> Your use of Yahoo! Groups is subject to:
http://docs.yahoo.com/info/terms/
