-
Chapter and Conference Paper
Task-related Item-Name Discovery Using Text and Image Data from the Internet
There is a huge number of data on the Internet that can be used for the development of machine learning in a robot or an AI agent. Utilizing this unorganized data, however, usually requires pre-collected datab...
-
Chapter and Conference Paper
Improved Kernel Density Estimation Self-organizing Incremental Neural Network to Perform Big Data Analysis
Plenty of data are generated continuously due to the progress in the field of network technology. Additionally, some data contain substantial noise, while other data vary their properties in according to vario...
-
Article
Effects of barbed suture during robot-assisted radical prostatectomy on postoperative tissue damage and longitudinal changes in lower urinary tract outcome
To compare the postoperative tissue damage and longitudinal changes in functional and patient-reported outcomes after vesicourethral anastomosis with barbed suture and nonbarbed suture in robot-assisted laparo...
-
Article
Placental recess accompanied by a T2 dark band: a new finding for diagnosing placental invasion
Our aim was to assess the usefulness of a new magnetic resonance imaging (MRI) finding, the placental recess, for diagnosing placental invasion.
-
Chapter and Conference Paper
Prediction of Tropical Storms Using Self-organizing Incremental Neural Networks and Error Evaluation
In this paper, we propose a route prediction method that uses a self-organizing incremental neural network (SOINN). For the training and testing of the neural network, only the latitude and longitude of the t...
-
Article
Genetic structure of the endangered red-crowned cranes in Hokkaido, Japan and conservation implications
The red-crowned crane in Japan was once considered extinct due to hunting and habitat destruction in late nineteenth century; however, in 1926, a small group of cranes was rediscovered in the Kushiro Mire in e...
-
Article
Open AccessRadiological and pathological characteristics of giant cell tumor of bone treated with denosumab
We describe a case of giant cell tumor of the proximal tibia with skip bone metastases of the ipsilateral femur in a 20-year-old man. After the neoadjuvant treatment with denosumab, plain radiographs and compu...
-
Chapter and Conference Paper
Robust Fast Online Multivariate Non-parametric Density Estimator
With the recent development of network and sensor technologies, vast amounts of data are being continuously generated in real time from real-world environments. Such data includes in many noise, and it is not ...
-
Chapter and Conference Paper
Density Estimation Method Based on Self-organizing Incremental Neural Networks and Error Estimation
In this paper, we propose an analysis of a self-organizing incremental neural network(SOINN), using new network adjusting algorithms, and a batched density estimation method combined with kernel density estima...
-
Chapter and Conference Paper
Self-Organizing Incremental Neural Network (SOINN) as a Mechanism for Motor Babbling and Sensory-Motor Learning in Developmental Robotics
Learning how to control arm joints for goal-directed reaching tasks is one of the earliest skills that need to be acquired by Developmental Robotics in order to scaffold into tasks of higher Intelligence. Moto...
-
Chapter and Conference Paper
Home Robots, Learn by Themselves
To build an intelligent robot, we must develop an autonomous mental development system that incrementally and speedily learns from humans, its environments, and electronic data. This paper presents an ultra-fa...
-
Article
An incremental online semi-supervised active learning algorithm based on self-organizing incremental neural network
An incremental online semi-supervised active learning algorithm, which is based on a self-organizing incremental neural network (SOINN), is proposed. This paper describes improvement of the two-layer SOINN to ...
-
Chapter and Conference Paper
Fast and Incremental Neural Associative Memory Based Approach for Adaptive Open-Loop Structural Control in High-Rise Buildings
A novel neural associative memory-based structural control method, coined as AMOLCO, is proposed in this study. AMOLCO is an open-loop control system that autonomously and incrementally learns to suppress the ...
-
Article
Open AccessA second generation genetic linkage map of Japanese flounder (Paralichthys olivaceus)
Japanese flounder (Paralichthys olivaceus) is one of the most economically important marine species in Northeast Asia. Information on genetic markers associated with quantitative trait loci (QTL) can be used in b...
-
Chapter and Conference Paper
Online Knowledge Acquisition and General Problem Solving in a Real World by Humanoid Robots
In this paper, the authors propose a three-layer architecture using an existing planner, which is designed to build a general problem-solving system in a real world. A robot, which has implemented the proposed...
-
Chapter and Conference Paper
Fast and Incremental Attribute Transferring and Classifying System for Detecting Unseen Object Classes
The problem of object classification when training and test classes are completely disjoint has recently become very popular in computer vision. To solve such problem, one needs to find common attributes of ob...
-
Chapter and Conference Paper
Unguided Robot Navigation Using Continuous Action Space
In this paper, we propose a new method for robot vision-based navigation. This method is distinct from other methods, in the sense that it works even when the actions are not pre-determined and when their spac...
-
Chapter and Conference Paper
Machine Learning Approaches for Time-Series Data Based on Self-Organizing Incremental Neural Network
In this paper, we introduce machine learning algorithms of time-series data based on Self-organizing Incremental Neural Network (SOINN). SOINN is known as a powerful tool for incremental unsupervised clusterin...
-
Chapter and Conference Paper
A Multidirectional Associative Memory Based on Self-organizing Incremental Neural Network
A multidirectional associative memory (AM) is proposed. It is constructed with three layer networks: an input layer, a memory layer, and an associate layer. The proposed method is able to realize many-to-many ...
-
Chapter and Conference Paper
How to Use the SOINN Software: User’s Guide (Version 1.0)
The Self-Organizing Neural Network (SOINN) is an unsupervised classifier that is capable of online incremental learning. Studies have been performed not only for improving the SOINN, but also for applying it t...
