Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
IN, CCS (Joint) |
2021-08-05 14:25 |
Online |
Online |
Digital Implement of 3-layered Neural Networks with Stochastic Activation, Shunting Inhibition, and a Dual-rail Backpropagation Yoshiaki Sasaki, Seiya Muramatsu, Kohei Nishida, Megumi Akai-Kasaya, Tetsuya Asai (Hokkaido Univ.) CCS2021-16 |
Stochastic computing (SC) is an arithmetic technique that enables various operations to be performed with a small number... [more] |
CCS2021-16 pp.7-13 |
NC, MBE (Joint) |
2020-03-05 10:20 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
An extension of the H_infinity learning to deep neural networks Yasuhiro Sugawara, Kiyoshi Nishiyama (Iwate University) NC2019-92 |
In recent years, deep neural networks have achieved remarkable research results. In this study, we propose a method to e... [more] |
NC2019-92 pp.95-100 |
NC, MBE (Joint) |
2019-03-05 09:30 |
Tokyo |
University of Electro Communications |
Novel Backpropagation Algorithm Considering Energy Rintaro Kanada, Masafumi Hagiwara (Keio Univ.) NC2018-63 |
In this paper, we propose a novel backpropagation(BP) algorithm considering energy. Neural network (NN) can be classifie... [more] |
NC2018-63 pp.105-110 |
MBE, NC (Joint) |
2018-03-14 15:30 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. |
Gradually Stacking Neural Network Shunya Sasaki, Masafumi Hagiwara (Keio Univ) NC2017-97 |
In this paper, we propose a neural network with multiple layers in a stepwise manner. Neural networks (NNs) become more ... [more] |
NC2017-97 pp.175-180 |
NLP |
2016-05-26 14:50 |
Kochi |
Kochi Univ. |
Decreasing Gradient of Sigmoid Functions in Back Propagation of Feed-Forward Neural Netowork Shinaburo Kittaka, Yoko Uwate, Nishio Yoshihumi (Tokushima Univ.) NLP2016-5 |
Our study is about the learning method of feed-forward neural network. Generally, the method of improvingitslearningisfo... [more] |
NLP2016-5 pp.25-28 |
MBE, NC (Joint) |
2014-11-21 11:00 |
Miyagi |
Tohoku University |
A Comparison of Back Propagation Learning between the Inverse-function Delayless Model and a Conventional Model Yuta Horiuchi (Tohoku Univ), Yoshihiro Hayakawa (SNCT), Takeshi Onomi, Koji Nakajima (Tohoku Univ) NC2014-26 |
For the combinatorial optimization problem using the hopfield model, avoidance of the local minimum problem is important... [more] |
NC2014-26 pp.7-10 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2014-09-02 15:45 |
Ibaraki |
|
Sampling Learning Algorithm by Oracle Distribution Sho Sonoda, Noboru Murata (Waseda Univ.) PRMU2014-52 IBISML2014-33 |
A new sampling learning algorithm for neural networks is proposed. Based on the integral representation of neural networ... [more] |
PRMU2014-52 IBISML2014-33 pp.137-142 |
IE, ITE-ME, IPSJ-AVM, ITE-CE [detail] |
2014-08-01 09:55 |
Chiba |
|
Study of Portrait Similarities in the Automatic System that Generates Portraits from Facial Images Wu Yuzhen, Makoto Enomoto, Jun Ohya (Waseda Univ) IE2014-22 |
This paper studies an automatic method that generates portraits by utilizing a neural network trained by facial features... [more] |
IE2014-22 pp.1-6 |
NLP |
2014-06-30 16:00 |
Miyagi |
Tohoku Univ. |
Backpropagation learning using inverse function delay-less model Yuta Horiuchi (Tohoku Univ.), Yoshihiro Hayakawa (SNCT), Takeshi Onomi, Koji Nakajima (Tohoku Univ.) NLP2014-25 |
The Inverse function Delayed (ID) model has been proposed as one of novel neural models. ID model has a oscillation capa... [more] |
NLP2014-25 pp.27-30 |
NLP |
2014-01-21 15:40 |
Hokkaido |
Niseko Park Hotel |
Neural Network learning using Inverse Function Delayless Model Yuta Horiuchi (Tohoku Univ.), Yoshihiro Hayakawa (SNCT), Shigeo Sato, Koji Nakajima (Tohoku Univ.) NLP2013-142 |
The Inverse function Delayed (ID) model has been proposed as one of novel neural models. The ID model has an ability of ... [more] |
NLP2013-142 pp.73-76 |
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 |
2011-01-25 11:45 |
Hokkaido |
Hokakido Univ. |
CNN Template Design that Obeyed BP Method from a Mathematical Point of View Masashi Nakagawa, Yoko Uwate, Yoshifumi Nishio (Tokushima Univ.) NLP2010-146 NC2010-110 |
In previous study, we have proposed template design method of cellular neural networks with back propagation algorithm.
... [more] |
NLP2010-146 NC2010-110 pp.123-127 |
NLP, CAS |
2010-08-03 10:30 |
Tokushima |
Naruto University of Education |
Template Design of CNN by BP with Annealing Noise Masashi Nakagawa, Yoko Uwate, Yoshifumi Nishio (Tokushima Univ.) CAS2010-51 NLP2010-67 |
In previous study, we proposed template design method of cellular neural networks with back propagation algorithm.
In t... [more] |
CAS2010-51 NLP2010-67 pp.93-98 |
NC |
2008-10-23 09:50 |
Miyagi |
Tohoku Univ. |
Effects of Refractoriness of Chaotic Neurodynamics for Acceleration of Learning of A Pattern Sequence Detector Susumu Nagatoishi, Osamu Araki (TUS) NC2008-38 |
The primary purpose of this study is to reveal the effects of refractoriness on learning. More specifically, we simulate... [more] |
NC2008-38 pp.13-18 |
DC |
2008-10-20 13:30 |
Tokyo |
National Center of Sciences |
Fault-Tolerant Multilayer Neural Networks for Multiple Weight-and-Neuron-Fault Kazuhiro Nishimura (Polytech Univ.), Masato Ootsu (JP Network), Tadayoshi Horita (Polytech Univ.), Itsuo Takanami (Ichinoseki kousen (former)) DC2008-22 |
The architecture of artificial neural networks, which are derived from brain mechanisms, are quite different from ordina... [more] |
DC2008-22 pp.1-6 |
NC |
2007-03-16 10:10 |
Tokyo |
Tamagawa University |
Learning nonlinear forward optics in generative models Satohiro Tajima, Masataka Watanabe (Tokyo Univ.) |
Visual processing is an inverse problem, say, the system needs to unravel the three dimensional representation of the wo... [more] |
NC2006-188 pp.11-16 |
PRMU, TL |
2005-03-17 09:45 |
Akita |
|
Hardware Implementation of Neural Networks for Real Time Image Processing Hirokazu Madokoro, Kazuhito Sato, Masaki Ishii (AITC) |
In this paper, we proposed the human skin color modeling and extraction method using Counter Propagation Network(CPN).
... [more] |
TL2004-46 PRMU2004-214 pp.13-18 |
NLP |
2004-05-18 11:45 |
Miyagi |
Tohoku Univ. |
* Jun Fukuhara, Yoshihiro Hayakawa, Koji Nakajima (Tohoku Univ.) |
Inverse Function Delayed model used in our research shows the negative resistance effect and the bistable output potenti... [more] |
NLP2004-4 pp.17-22 |