Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
MBE, NC (Joint) |
2022-03-02 11:00 |
Online |
Online |
Learning of a stacked autoencoder with regularizers added to the cost function, evaluation of their effectiveness, and clarification of its information compression mechanism Masumi Ishikawa (Kyutech) NC2021-49 |
Deep learning has a serious drawback in that the resulting models tend to be a black box, hence hard to understand. A sp... [more] |
NC2021-49 pp.17-22 |
NLP, MICT, MBE, NC (Joint) [detail] |
2022-01-23 12:10 |
Online |
Online |
Deep learning of mixture of continuous and categorical data with regularizers added to the cost function and evaluation of the effectiveness of sparse modeling Masumi Ishikawa (Kyutech) NC2021-45 |
Deep learning has a serious drawback in that the resulting models tend to be a black box, hence hard to understand. A sp... [more] |
NC2021-45 pp.65-70 |
NC, IBISML, IPSJ-BIO, IPSJ-MPS [detail] |
2020-06-29 13:50 |
Online |
Online |
Performance comparison of autoencoders and sparse PCAs Masumi Ishikawa (Kyutech) NC2020-4 IBISML2020-4 |
Principal component analysis (PCA) is an effective tool for clarifying data structure. Each principal component includes... [more] |
NC2020-4 IBISML2020-4 pp.21-26 |
NC, MBE (Joint) |
2020-03-06 14:55 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
Efficient cluster mapping for conditions of weather based on combination of self-organizing map and hierarchical clustering Kazuki Osawa, Keiji Kamei (NIT), Masumi Ishikawa (KIT) NC2019-113 |
Recently, applications of Deep Learning(AI) for solving social problems have been frequently proposed. However, there ar... [more] |
NC2019-113 pp.213-218 |
NC, MBE (Joint) |
2020-03-06 16:10 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
Sparse modeling of deep classification networks with layer-wise greedy learning and various regularization terms Masumi Ishikawa (Kyutech) NC2019-116 |
Training of deep networks is difficult due to vanishing gradients. To overcome this difficulty, layer-wise greedy learni... [more] |
NC2019-116 pp.231-236 |
NC, MBE |
2019-12-06 15:40 |
Aichi |
Toyohashi Tech |
Prevention of redundant representations and of the black box in stacked autoencoders Masumi Ishikawa (Kyutech) MBE2019-56 NC2019-47 |
Recent progress in deep learning (DL) is remarkable and its recognition capability is said to surpass that of humans. Th... [more] |
MBE2019-56 NC2019-47 pp.67-72 |
NC, MBE (Joint) |
2019-03-04 17:00 |
Tokyo |
University of Electro Communications |
Towards understandable deep learning in stacked autoencoders Masumi Ishikawa (Kyutech) NC2018-62 |
Recent progress of deep learning(DP) is remarkable and its recognition ability is said to surpass that of humans. The ac... [more] |
NC2018-62 pp.99-104 |
NC |
2011-10-20 10:20 |
Fukuoka |
Ohashi Campus, Kyushu Univ. |
Reduction of order for states in a board game using Self-Organizing Maps Yuuki Kakizoe, Keiji Kamei (NIT), Masumi Ishikawa (KIT) NC2011-61 |
Generally speaking, to make agents which play board games such as Chess, Syogi and Othello is associated with difficulty... [more] |
NC2011-61 pp.95-100 |
NC, MBE (Joint) |
2010-03-09 14:35 |
Tokyo |
Tamagawa University |
Localization of Robots Based on Learning of Filters for Image features Mariko Oki, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2009-107 |
In feature-based localization of a mobile robot, it is difficult to decide what features to use for localization.To trai... [more] |
NC2009-107 pp.113-118 |
NC, MBE (Joint) |
2010-03-09 15:00 |
Tokyo |
Tamagawa University |
Reinforcement Learning with Internal Rewards Based on Error in a Grid-based Map Takafumi Kai, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2009-108 |
The present paper proposes to search a method for an agent to find the shortest path by reinforcement learning in varyin... [more] |
NC2009-108 pp.119-124 |
NC, MBE (Joint) |
2010-03-09 16:00 |
Tokyo |
Tamagawa University |
Dual Map Building and Localization for Mobile Robots Based on Panoramic Images Youbo Cai, Masumi Ishikawa (Kyusyu Inst. of Tech.) NC2009-110 |
[more] |
NC2009-110 pp.131-136 |
NC, MBE (Joint) |
2010-03-09 16:50 |
Tokyo |
Tamagawa University |
Hierarchical Architecture with Evolving Modular Networks and Modular Reinforcement Learning Naoyuki Kanamoto, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2009-112 |
We propose a hierarchical architecture composed of a characteristic learning layer which models characteristics of a tar... [more] |
NC2009-112 pp.143-148 |
NC, MBE (Joint) |
2010-03-10 15:25 |
Tokyo |
Tamagawa University |
Several Methods of Curiosity-Driven Multi-Swarm Search Hong Zhang, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2009-140 |
In this paper, we propose several methods of curiosity-driven multi-swarm search, i.e. multiple particle swarm optimizer... [more] |
NC2009-140 pp.309-314 |
NC, MBE (Joint) |
2009-03-12 16:05 |
Tokyo |
Tamagawa Univ. |
Effects of Canonical Particle Swarm Optimizer with Diversive Curiosity Hong Zhang, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2008-137 |
This paper proposes a new method, named Canonical Particle Swarm Optimizer with Diversive Curiosity (CPSO/DC), which is ... [more] |
NC2008-137 pp.201-206 |
NC, MBE (Joint) |
2009-03-13 09:45 |
Tokyo |
Tamagawa Univ. |
Emergence of Behaviors based on the Desire for Existence by Reinforcement Learning Mikio Morita, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2008-150 |
[more] |
NC2008-150 pp.279-283 |
NC, MBE (Joint) |
2009-03-13 10:10 |
Tokyo |
Tamagawa Univ. |
Reinforcement Learning with Internal Rewards Based on Error in a Grid Based Map Yoshifumi Tanaka, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2008-151 |
[more] |
NC2008-151 pp.285-290 |
NC, NLP |
2008-06-26 15:35 |
Okinawa |
University of the Ryukyus |
[Fellow Memorial Lecture]
From forgetting to curiosity Masumi Ishikawa (Kyutech) NLP2008-6 NC2008-16 |
The study to which IEICE conferred Fellow started by introducing a concept of "forgetting" to learning of neural network... [more] |
NLP2008-6 NC2008-16 pp.31-32 |
NC, MBE (Joint) |
2008-03-13 10:20 |
Tokyo |
Tamagawa Univ |
Action planning of a mobile robot based on intrinsic motivation Naoyuki Yamamoto, Masumi Ishikawa (KIT) NC2007-163 |
Developmental robotics is an emergent area of research at the intersection of robotics and development sciences. In this... [more] |
NC2007-163 pp.301-306 |
NC, MBE (Joint) |
2008-03-13 10:40 |
Tokyo |
Tamagawa Univ |
Graph-based Maps Formation for Mobile Robots by Hidden Markov Models Muhammad Aziz Muslim, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2007-164 |
The present paper proposes a probabilistic approach to recognizing the environment of a mobile robot and to generate a g... [more] |
NC2007-164 pp.307-312 |
NC, MBE (Joint) |
2008-03-14 14:50 |
Tokyo |
Tamagawa Univ |
Model Selection of Canonical Particle Swarm Optimizer by EPSO: Meta-Optimization Hong Zhang, Masumi Ishikawa (Kyushu Inst. of Tech.) NC2007-196 |
We have proposed Evolutionary Particle Swarm Optimization, EPSO, which can estimate PSO models for efficiently solving v... [more] |
NC2007-196 pp.495-500 |