Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NLP, CCS |
2024-06-06 15:20 |
Fukuoka |
West Japan General Exhibition Center AIM |
An Efficient Deep Learning Method by Sequential Insertion of Hidden Layers Kentaro Toki, Hidehiro Nakano (Tokyo City Univ.) |
[more] |
|
NLP, CCS |
2024-06-07 11:20 |
Fukuoka |
West Japan General Exhibition Center AIM |
Developmennt of computing circuit for swarm intelligence algorithm based on spiking-neural oscillator networks Tomoyuki Sasaki (SIT), Hidehiro Nakano (TCU) |
[more] |
|
NLP, CCS |
2024-06-07 15:30 |
Fukuoka |
West Japan General Exhibition Center AIM |
Solving Time-Dependent TSP by Ant Colony Optimization Consisting of Various Types of Ants Haruki Shikata, Hidehiro Nakano (Tokyo City Univ.) |
[more] |
|
NLP, MSS |
2024-03-13 17:20 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
Application of Data Augmentation in Japanese Foundation Models Kazuki Era, Hidehiro Nakano (Tokyo City Univ.) MSS2023-84 NLP2023-136 |
One of the recent topics is data augmentation. Data augmentation is a method of augmenting training data to improve the ... [more] |
MSS2023-84 NLP2023-136 pp.66-69 |
NLP, MSS |
2024-03-14 10:25 |
Misc. |
Kikai-Shinko-Kaikan Bldg. |
A Particle Swarm Optimizer Based on Chaotic Spiking Oscillators with Dynamic Thresholds for Velocity Vectors Ahmed Ali, Hidehiro Nakano (Tokyo City Univ.) MSS2023-87 NLP2023-139 |
Particle Swarm Optimization (PSO) is a metaheuristic algorithm known for solving complex optimization problems. Despite ... [more] |
MSS2023-87 NLP2023-139 pp.77-82 |
CCS |
2023-11-12 10:25 |
Toyama |
Toyama Prefectural University |
Analysis of a simple network topology for optimizer based on spiking-neural oscillator networks Tomoyuki Sasaki (SIT), Hidehiro Nakano (TCU) CCS2023-34 |
Optimizer based on Spiking Neural-oscillator Networks (OSNNs) are one of the deterministic PSO methods, which are based ... [more] |
CCS2023-34 pp.53-57 |
CCS, NLP |
2023-06-08 15:35 |
Tokyo |
Tokyo City Univ. |
A place and route method in AQFP circuits using multi-objective optimization Syota Kasai, Hidehiro Nakano (Tokyo City Univ.) NLP2023-18 CCS2023-6 |
In recent years, research has been conducted on AQFP circuits, which are superconducting logic circuits that consume les... [more] |
NLP2023-18 CCS2023-6 pp.21-24 |
NLP |
2023-05-13 11:15 |
Fukushima |
Kenshin Koriyama Cultural Center (Koriyama, Fukushima) |
Parameter adjustment methods of ACO based on moving costs in time-dependent TSP Teppei Yamauchi, Hidehiro Nakano (Tokyo City Univ.) NLP2023-4 |
The Time Dependent Traveling Salesman Problem (TDTSP) is a combinatorial optimization problem with dynamically changing ... [more] |
NLP2023-4 pp.16-19 |
CCS |
2023-03-26 13:35 |
Hokkaido |
RUSUTSU RESORT |
Analysis of learning performance in CycleGAN by applying data augmentation to few data Syuhei Kanzaki, Hidehiro Nakano (Tokyo City Univ.) CCS2022-72 |
In machine learning and deep learning, a huge amount of data is required for training. The image generation model GAN ex... [more] |
CCS2022-72 pp.54-58 |
NLP, MSS |
2023-03-17 15:45 |
Nagasaki |
(Primary: On-site, Secondary: Online) |
Improving Recognition Accuracy in Contrastive Learning by Weighted Similarity Based on Data Source Ryotaro Sei, Hidehiro Nakano (Tokyo City Univ.) MSS2022-107 NLP2022-152 |
[more] |
MSS2022-107 NLP2022-152 pp.214-219 |
NLP, MSS |
2023-03-17 16:05 |
Nagasaki |
(Primary: On-site, Secondary: Online) |
Lightweighting Noisy Student Semi-Supervised Learning by Applying MobileNet Yuga Morishima, Hidehiro Nakano (Tokyo City Univ.) MSS2022-108 NLP2022-153 |
Recently, Convolutional Neural Networks (CNNs) have attracted much attention in various fields such as image classificat... [more] |
MSS2022-108 NLP2022-153 pp.220-224 |
NLP, MSS |
2023-03-17 16:25 |
Nagasaki |
(Primary: On-site, Secondary: Online) |
Investigation on improving diversity of options in option-critic reinforcement learning Aya Nakagawa, Hidehiro Nakano (Tokyo City Univ.) MSS2022-109 NLP2022-154 |
Recently, reinforcement learning has been attracting attention in various fields such as automatic control and game AI. ... [more] |
MSS2022-109 NLP2022-154 pp.225-230 |
CCS |
2022-11-18 14:30 |
Mie |
(Primary: On-site, Secondary: Online) |
Particle swarm optimization considering a positive and negative inertia terms by Levy distribution Sohei Kusaka, Hidehiro Nakano (Tokyo City Univ.) CCS2022-57 |
Particle Swarm Optimization (PSO) is known as a type of swarm intelligence algorithms. The inertia constant of each sear... [more] |
CCS2022-57 pp.71-75 |
CCS |
2022-11-18 14:55 |
Mie |
(Primary: On-site, Secondary: Online) |
Particle swarm optimization using bit representation of state variables as random dynamics Masashi Nitanda, Hidehiro Nakano (Tokyo City Univ.) CCS2022-58 |
[more] |
CCS2022-58 pp.76-80 |
CCS |
2022-11-18 15:20 |
Mie |
(Primary: On-site, Secondary: Online) |
Multi-domain translation from few data by CycleGAN applying data augmentation Syuhei Kanzaki, Hidehiro Nakano (Tokyo City Univ.) CCS2022-59 |
In machine learning and deep learning, a huge amount of data is required for training. The image generation model GAN ex... [more] |
CCS2022-59 pp.81-84 |
CCS |
2022-11-18 16:00 |
Mie |
(Primary: On-site, Secondary: Online) |
Investigation for the coupling interactions in swarm intelligence algorithm based on spiking neural-oscillator networks Tomoyuki Sasaki (SIT), Hidehiro Nakano (TCU) CCS2022-60 |
Optimizer based on Spiking Neural-oscillator Networks (OSNNs) are deterministic swarm intelligence algorithms which intr... [more] |
CCS2022-60 pp.85-90 |
IN, CCS (Joint) |
2022-08-04 10:00 |
Hokkaido |
Hokkaido University(Centennial Hall) (Primary: On-site, Secondary: Online) |
Investigation on Applying Data Augmentation to CycleGAN Syuhei Kanzaki, Hidehiro Nakano (Tokyo City Univ.) CCS2022-26 |
In machine learning and deep learning, a huge amount of data is required for training. The image generation model GAN ex... [more] |
CCS2022-26 pp.1-5 |
CCS, NLP |
2022-06-09 13:50 |
Osaka |
(Primary: On-site, Secondary: Online) |
Improvement of Learning Performance by Using a Symmetric Constraint Condition in PPO Naoki Iwaya, Hidehiro Nakano (Tokyo City Univ.) NLP2022-3 CCS2022-3 |
Deep Reinforcement Learning (DRL) is an algorithm of learning the optimal action from the experiences. PPO KL Penalty, a... [more] |
NLP2022-3 CCS2022-3 pp.13-16 |
CCS, NLP |
2022-06-09 14:15 |
Osaka |
(Primary: On-site, Secondary: Online) |
Improvement of Recognition Accuracy by Sequential Execution of Unsupervised Learning and Semi-supervised Learning Hiroki Murakami, Hidehiro Nakano (Tokyo City Univ.) NLP2022-4 CCS2022-4 |
In this study, we propose a sequential learning method that improves recognition accuracy by alternately utilizing the k... [more] |
NLP2022-4 CCS2022-4 pp.17-22 |
CCS, NLP |
2022-06-09 14:55 |
Osaka |
(Primary: On-site, Secondary: Online) |
Basic Performance of CNNs Using Dynamic Filters Based on Octave Convolution Kiyotaka Matono, Hidehiro Nakano (Tokyo City Univ.) NLP2022-5 CCS2022-5 |
The methods of using dynamic filters for convolutional neural networks (CNNs) have attracted attentions. In recent years... [more] |
NLP2022-5 CCS2022-5 pp.23-26 |