Tetsuo Furukawa

Learn More
This paper proposes an extension of the self-organizing map (SOM), in which the mapping objects themselves are self-organizing maps. Thus a "SOM of SOMs" is presented, which we refer to as a SOM(2). A SOM(2) has a hierarchical structure consisting of a single parent SOM and a set of child SOMs. Each child SOM is trained to represent the distribution of a(More)
The speed of signal conduction is a factor determining the temporal properties of individual neurons and neuronal networks. We observed very different conduction velocities within the receptive field of fast-type On-Off transient amacrine cells in carp retina cells, which are tightly coupled to each other via gap junctions. The fastest speeds were found in(More)
This study aims to develop a generalized framework of an SOM called a modular network SOM (mnSOM). The mnSOM has an array structure consisting of functional modules that are trainable neural networks, e.g., multi-layer perceptrons (MLPs), instead of the vector units of the conventional SOM. In the case of MLP-modules, an mnSOM learns a group of systems or(More)
Proposed is a new task segmentation method in navigation of mobile robots by a modular network SOM (mnSOM). mnSOM is an extension of SOM in that a function module instead of a vector unit is used to increase its representation capability. It has the ability of both segmentation and interpolation. During learning, modules in mnSOM compete with each other to(More)
BACKGROUND Acute decompensated heart failure (ADHF) is generally considered to be a problem of fluid volume overload, therefore accurately quantifying the degree of fluid accumulation is of critical importance in assessing whether adequate decongestion has been achieved. The aim of this study was to develop and validate a method to quantify the degree of(More)
Proposed is a new approach to task segmentation in a mobile robot by a modular network SOM (mnSOM). In a mobile robot the standard mnSOM is not applicable as it is, because it is based on the assumption that class labels are known a priori. In a mobile robot, only a sequence of data without segmentation is available. Hence, we propose to decompose it into(More)
Abstract — This study presents a new concept that generalizes the self-organizing map (SOM) by adopting the idea of modular network, which we call “modular network SOM (mnSOM)”. In the mnSOM, each codebook vector in the conventional SOM is replaced by a functional module which is a neural network. With mnSOM, the application targets can be widely expanded(More)
This paper proposes an extension of an SOM called the “SOM of SOMs,” or SOM, in which objects to be mapped are self-organizing maps. In SOM, each nodal unit of a conventional SOM is replaced by a function module of SOM. Therefore, SOM can be regarded as a variation of a modular network SOM (mnSOM). Since each child SOM module in SOM is trained to represent(More)