Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, NLP |
2013-01-24 09:30 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Multilayer Perceptron Search Making Good Use of Singular Regions Seiya Satoh, Ryohei Nakano (Chubu Univ.) NLP2012-104 NC2012-94 |
In a search space of multilayer perceptron having J hidden units, MLP(J), there exists a singular flat region created by... [more] |
NLP2012-104 NC2012-94 pp.1-6 |
NC, NLP |
2013-01-24 09:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Multilayer Perceptron Model Selection Using Sampling Utilizing Singularity Stairs Following Takayuki Ohwaki, Ryohei Nakano (Chubu Univ.) NLP2012-105 NC2012-95 |
Multilayer perceptron (MLP) is one of singular statistical models, where it is not guaranteed that any parameter is uniq... [more] |
NLP2012-105 NC2012-95 pp.7-12 |
NC, NLP |
2013-01-24 10:10 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Analysis of Medical Treatment Data using Inverse Reinforcement Learning Hideki Asoh, Masanori Shiro, Toshihiro Kamishima, Shotaro Akaho (AIST), Takahide Kohro (Univ. of Tokyo Hospital) NLP2012-106 NC2012-96 |
It is an important issue to utilize large amount of medical records which are accumulated on medical information systems... [more] |
NLP2012-106 NC2012-96 pp.13-17 |
NC, NLP |
2013-01-24 10:30 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Control of the falling cat motion by using path-integral reinforcement learning Daichi Nakano, Shin-ichi Maeda, Shin Ishii (Kyoto Univ) NLP2012-107 NC2012-97 |
The falling-cat motion is a motion for controlling the cat's posture under no existence of external force. To obtain a c... [more] |
NLP2012-107 NC2012-97 pp.19-24 |
NC, NLP |
2013-01-24 10:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Significance of non-stationary of dynamics for learning cooperative behavior Akihiro Tawa, Shin-ichi Maeda, Shin Ishii (Kyoto Univ.) NLP2012-108 NC2012-98 |
To understand how cooperative behaviors emerge is important in the field of multi-agent system research. Although this e... [more] |
NLP2012-108 NC2012-98 pp.25-30 |
NC, NLP |
2013-01-24 11:10 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
depth estimation from microscopic images using Bayesian inference Yasuhiro Imoto, Shin-ichi Maeda, Shin Ishii (Kyoto Univ.) NLP2012-109 NC2012-99 |
In cellular biology, it is important to know 3D cellular shape to understand the cellular function. However, existing mi... [more] |
NLP2012-109 NC2012-99 pp.31-36 |
NC, NLP |
2013-01-24 11:30 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Tensor Decomposition using Self-Organizing Map and Missing Data Estimation Koji Hashimoto, Toru Iwasaki, Tetsuo Furukawa (Kyutech) NLP2012-110 NC2012-100 |
Tensor-Decomposition Self-Organizing Map (TD-SOM) is a nonlinear tensor decomposition method based on SOM. The aim of th... [more] |
NLP2012-110 NC2012-100 pp.37-42 |
NC, NLP |
2013-01-24 12:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Study of qusai-Newton training algorithm on parallel distributed environment Makoto Saiki, Yoshihiko Sakashita, Hiroshi Ninomiya (Shonan Inst. of Tech.) NLP2012-111 NC2012-101 |
This paper describes the feasibility of quasi-Newton method for training feedforward neural networks on the parallel dis... [more] |
NLP2012-111 NC2012-101 pp.43-48 |
NC, NLP |
2013-01-24 13:10 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Text Classification Using Context-Tree Weighting Algorithm for Semi-Supervised Leaning Tomohiro Obata, Manabu Kobayashi, Yoshihiko Sakashita (Shonan Inst. of Tech.) NLP2012-112 NC2012-102 |
The Text Classification problem has been investigated by various techniques, such as a vector space model, a support vec... [more] |
NLP2012-112 NC2012-102 pp.49-53 |
NC, NLP |
2013-01-24 13:30 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Probabilistic flows of inhabitants in urban areas and self-organization in housing markets of a city designated by ordinance Takao Hishikawa, Jun-ichi Inoue (Hokkaido Univ.) NLP2012-113 NC2012-103 |
We propose a very simple probabilistic model to
explain the rent distribution of housing market in Sapporo city.
We ... [more] |
NLP2012-113 NC2012-103 pp.55-60 |
NC, NLP |
2013-01-24 13:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
A probabilistic model of television commercial markets Hiroyuki Kyan, Jun-ichi Inoue (Hokkaido Univ.) NLP2012-114 NC2012-104 |
We propose a simple probabilistic model of zapping process of television viewers.
Our model might be regarded as a `t... [more] |
NLP2012-114 NC2012-104 pp.61-66 |
NC, NLP |
2013-01-24 14:10 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Characterizing financial crisis by means of the Three states random field Ising model Mitsuaki Murota, Jun-ichi Inoue (Hokkaido Univ.) NLP2012-115 NC2012-105 |
We extend the formulation of time-series prediction using Ising model given by Kaizouji (2001) or Higano et.al. (2012) b... [more] |
NLP2012-115 NC2012-105 pp.67-72 |
NC, NLP |
2013-01-24 14:30 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Calculating finite-time Lyapunov exponents in time delayed dynamical systems Kazutaka Kanno, Atsushi Uchida (Saitama Univ.) NLP2012-116 NC2012-106 |
Lyapunov exponents represents a exponential expansion (construction) rate of a innitesimal perturbation to an orbit of ... [more] |
NLP2012-116 NC2012-106 pp.73-78 |
NC, NLP |
2013-01-24 14:50 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Asynchronous Cellular Automata Based Hair Cell Models and their Fundamental Characteristics Hironori Ishimoto, Hiroyuki Torikai (Osaka Univ) NLP2012-117 NC2012-107 |
In the mammalian inner ear, the basilar membrane vibrates in response to a sound wave and the inner hair cells transform... [more] |
NLP2012-117 NC2012-107 pp.79-84 |
NC, NLP |
2013-01-24 15:20 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
[Invited Talk]
Life as a Dynamical System
-- Nonlinear Dynamics of Cultured Neural Networks -- Kazutoshi Gohara (Hokkaido Univ) NLP2012-118 NC2012-108 |
[more] |
NLP2012-118 NC2012-108 pp.85-86 |
NC, NLP |
2013-01-24 16:20 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Insensitive Particle Swarm Optimizers and Application to Exploring Periodic Points Kazuki Maruyama, Toshimichi Saito (Hosei Univ.) NLP2012-119 NC2012-109 |
This paper studies an insensitive particle swarm optimizer (IPSO) for multi-solution problems.
The IPSO is governed by... [more] |
NLP2012-119 NC2012-109 pp.87-91 |
NC, NLP |
2013-01-24 16:40 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Hardware Implementation of the Inhibitory Connected Pulse Coupled Neural Network using FPGA Masahiro Yoshihara, Soichiro Ikuno, Hiroaki Kurokawa (Tokyo Univ of Tech) NLP2012-120 NC2012-110 |
Image segmentation is one of an image processing. Image segmentation is used object recognition and object detection. Pu... [more] |
NLP2012-120 NC2012-110 pp.93-98 |
NC, NLP |
2013-01-24 17:00 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Rotation Angle Measurement System by Using Two Resonators and One Oscillator Including Printed Spiral Inductors. Takahiro Kuroko, Yuji Tanada, Masayuki Yamauchi (HIT) NLP2012-121 NC2012-111 |
We have developed and proposed some systems that measured rotation angles
of rotators, which are motors, bolts, and so ... [more] |
NLP2012-121 NC2012-111 pp.99-104 |
NC, NLP |
2013-01-24 17:20 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Design of a threshold-coupled CMOS chaos circuit using voltage/current waveform sampling Seiji Uenohara, Daisuke Atuti, Kenji Matsuzaka, Takashi Morie (Kyutech), Kazuyuki Aihara (Univ. of Tokyo) NLP2012-122 NC2012-112 |
In order to develop large-scale coupled nonlinear dynamical systems using CMOS integrated circuits,
we propose a thresh... [more] |
NLP2012-122 NC2012-112 pp.105-110 |
NC, NLP |
2013-01-24 17:40 |
Hokkaido |
Hokkaido University Centennial Memory Hall |
Bifurcation of Simple Spiking Neuron Model with Filters Shota Kirikawa, Toshimichi Saito (Hosei Univ.) NLP2012-123 NC2012-113 |
This paper studies a simple spiking neuron with filtered base signal.
The base signal is made by applying two kinds of... [more] |
NLP2012-123 NC2012-113 pp.111-114 |