Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, MBE (Joint) |
2023-03-14 10:20 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
Study on a robust and accurate deep learning method Shoma Noguchi, Shogo Taneda, Yukari Yamauchi (Nihon Univ.) NC2022-101 |
In deep learning, there are many hyperparameters that must be determined in advance, and it is known that the accuracy v... [more] |
NC2022-101 pp.54-59 |
NC, MBE (Joint) |
2023-03-14 15:50 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
Curiosity-based deep reinforcement learning with profit sharing Kouki Hayashi, Kazuma Yamaguchi, Yukari Yamauchi (Nihon Univ.) NC2022-107 |
Recently, "DQN with PS," which incorporates profit sharing in deep reinforcement learning, was proposed. This method sp... [more] |
NC2022-107 pp.90-93 |
NC, MBE (Joint) |
2023-03-15 10:30 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
Proposal of Node Fusion in Sparse DenseNet Shogo Taneda, Shoma Noguchi, Yukari Yamauchi (Nihon Univ.) NC2022-110 |
Gao Huang et al. proposed a deep learning model called DenseNet. This deep learning model successfully prevents informat... [more] |
NC2022-110 pp.105-108 |
NC, MBE (Joint) |
2023-03-15 10:55 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
Proposal for Mini-Batch Learning in Clustering V-SOINN Tetsuya Komura, Rintaro Funada, Yukari Yamauchi (Nihon Univ.) NC2022-111 |
Yamazaki et al. proposed a learning method called Self-Organizing Incremental Neural Network (SOINN). This method is an ... [more] |
NC2022-111 pp.109-112 |
NC, MBE (Joint) |
2023-03-15 11:20 |
Tokyo |
The Univ. of Electro-Communications (Primary: On-site, Secondary: Online) |
Optimizing SOINN Space for High-Dimensional Data Robustness Yu Takahagi, Yusuke Tsuchida, Yukari Yamauchi (Nihon Univ.) NC2022-112 |
Yamazaki et al. proposed a learning method called Self-Organizing Incremental Neural Network (SOINN). This method is an ... [more] |
NC2022-112 pp.113-118 |
DC |
2022-03-01 16:10 |
Tokyo |
Kikai-Shinko-Kaikan Bldg. (Primary: On-site, Secondary: Online) |
An Estimation Method of Defect Types for Multi-cycle Capture Testing Using Artificial Neural Networks and Fault Detection Information Natsuki Ota, Toshinori Hosokawa (Nihon Univ.), Koji Yamazaki (Meiji Univ.), Masayuki Arai, Yukari Yamauchi (Nihon Univ.) DC2021-77 |
[more] |
DC2021-77 pp.75-80 |
CPSY, DC, IPSJ-SLDM, IPSJ-EMB, IPSJ-ARC [detail] |
2021-03-26 11:00 |
Online |
Online |
An Estimation Method of a Defect Types for Suspected Fault Lines in Logical Faulty VLSI Using Neural Networks Natsuki Ota, Toshinori Hosokawa (Nihon Univ.), Koji Yamazaki (Meiji Univ.), Yukari Yamauchi, Masayuki Arai (Nihon Univ.) CPSY2020-61 DC2020-91 |
Since fault diagnosis methods for specified fault models might cause misprediction and non-prediction, a fault diagnosis... [more] |
CPSY2020-61 DC2020-91 pp.67-72 |
NC, MBE (Joint) |
2021-03-03 13:00 |
Online |
Online |
Hybrid Sparsity in Convolutional Neural Networks Shoma Noguchi, Yukari Yamauchi (Nihon Univ.) NC2020-46 |
Convolutional neural networks (CNNs) have achieved high accuracy in areas such as image classification and object detect... [more] |
NC2020-46 pp.21-24 |
NC, MBE (Joint) |
2021-03-04 16:25 |
Online |
Online |
Hierarchical Feature Extraction for Dynamic Q-Network Taishi Komatsu, Yukari Yamauchi (Nihon Univ.) NC2020-62 |
Recently, Convolutional Neural Networks (CNN), which have been successful in the field of image recognition, use a hiera... [more] |
NC2020-62 pp.112-116 |
NC, MBE (Joint) |
2021-03-04 16:50 |
Online |
Online |
A3C with Deterministic Policy Gradient Yu Takahagi, Yukari Yamauchi (Nihon Univ.) NC2020-63 |
Mnih et al. proposed a learning method called Asynchronous Advantage Actor-Critic (A3C). This method explores asynchrono... [more] |
NC2020-63 pp.117-120 |
NC, MBE (Joint) |
2021-03-05 10:55 |
Online |
Online |
Proposal of Self-Organizing Incremental Neural Network based on Sparsity Yuta Morikawa, Yukari Yamauchi (Nihon Univ) NC2020-67 |
[more] |
NC2020-67 pp.139-144 |
NC, MBE (Joint) |
2021-03-05 13:25 |
Online |
Online |
Applying Ensemble Learning in Relay BP Keisuke Toyama, Yukari Yamauchi (Nihon Univ.) NC2020-70 |
Convolutional Neural Network (CNN) is one of the network models that can produce highly accurate output even though it u... [more] |
NC2020-70 pp.157-162 |
NC, MBE (Joint) |
2021-03-05 13:50 |
Online |
Online |
DCSOM with Ensemble Learning Classifier Akito Takahashi, Yukari Yamauchi (Nihon Univ) NC2020-71 |
Deep Convolutional Self-Organizing Map (DCSOM) which extracts visual features from images by using self-organizing maps ... [more] |
NC2020-71 pp.163-168 |
NC, MBE (Joint) |
2021-03-05 14:30 |
Online |
Online |
Adaptive Optimization Method in Artificial Neural Network that Independ on Learning Rate Tetsuya Sato, Yukari Yamauti (Nihon Univ.) NC2020-72 |
What kind of optimizer is used in machine learning is an important issue. SGD has high accuracy but slow convergence and... [more] |
NC2020-72 pp.169-173 |
MBE, NC, NLP, CAS (Joint) [detail] |
2020-10-30 15:20 |
Online |
Online |
Fusion of feature extraction and reinforcement learning for Dynamic Q-Network Taishi Komatsu, Yukari Yamauchi (NU) NC2020-22 |
[more] |
NC2020-22 pp.72-76 |
MBE, NC, NLP, CAS (Joint) [detail] |
2020-10-30 15:45 |
Online |
Online |
A Proposal of Self-Organizing Map Based on Attribute Information with Attenuate Rate Tetsuya Sato, Yukari Yamauti (Nihon Univ.) NC2020-23 |
Self-organizing Maps(SOM) is a simple algorithm, has excellent clustering capabilities, and can create a nonlinear model... [more] |
NC2020-23 pp.77-82 |
NC, MBE (Joint) |
2020-03-05 13:50 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
A Proposal of Self-Organizing Maps Based on Learning with Attribute Information Tetsuya Sato, Yukari Yamauti (Nihon Univ.) NC2019-96 |
Self-organizing maps(SOM) is a simple algorithm, and has excellent clustering capabilities. However, since SOM performs ... [more] |
NC2019-96 pp.119-124 |
NC, MBE (Joint) |
2020-03-06 10:20 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
Feature Extraction by Competitive Learning for Dynamic Q-Network Taishi Komatsu, Yukari Yamauchi (NU) NC2019-106 |
Deep Q-Network is a reinforcement learning algorithm that performs feature extraction by convolution from state space in... [more] |
NC2019-106 pp.175-179 |
MBE, NC |
2019-10-12 10:50 |
Miyagi |
|
An Optimization for Classification by Self-Organizing Maps Based on Attribute Information Tetsuya Sato (Nihon Univ.), Kazuma Tsuchida (STUDIO ONE OR EIGHT), Yukari Yamauti (Nihon Univ.) MBE2019-41 NC2019-32 |
Self-Organizing Map (SOM) is a simple algorithm that has excellent clustering capabilities and adapts continuous changes... [more] |
MBE2019-41 NC2019-32 pp.59-63 |
VLD, DC, CPSY, RECONF, CPM, ICD, IE, IPSJ-SLDM, IPSJ-EMB, IPSJ-ARC (Joint) [detail] |
2018-12-06 10:55 |
Hiroshima |
Satellite Campus Hiroshima |
On the Generation of Random Capture Safe Test Vectors Using Neural Networks Sayuri Ochi, Kenichirou Misawa, Toshinori Hosokawa, Yukari Yamauchi, Masayuki Arai (Nihon Univ.) VLD2018-51 DC2018-37 |
Excessive capture power consumption at scan testing causes the excessive IR drop and it might cause test-induced yield l... [more] |
VLD2018-51 DC2018-37 pp.89-94 |