An architecture of self‐organizing map for temporal signal processing and its application to a Braille recognition task

Abstract

SUMMARYA self-organizing map (SOM) performs a mapping of an object preserving its topological relations between input and output spaces, and also can be seen as a coordinate transformer that preserves adjacency relations. Since the standard SOM cannot deal with temporal data intrinsically, in this paper we provide new feedback pathways around the competitive layer to refer to context information of the past history. An extra output layer is added next to the competitive layer to represent secondary candidates and a quantitative measure of confidence. From the viewpoint of its structural similarities, we refer to this architecture as an Elman-type feedback SOM. In order to clarify the effectiveness of the proposed model, we then adopt a temporal signal processing task of Braille recognition. Braille is a character set for visually impaired people made up of 6 dots on a 3 by 2 grid. When Braille is read by running the fingertip over the characters, the vertical axis can be seen as providing spatial information and the horizontal axis as providing temporal information. As a result of computer simulations with partially common four city names, we confirm that the proposed model can recognize them appropriately. In addition, we find that this approach is robust to both the temporal elasticity and spatial displacement. Moreover, when we conduct an analysis with the neuro-bar model, we find that the Braille recognition task is executed based on a series of state transition along a type of pathway that has been developed during training.

A consideration on visualization of temporal signals by feedback SOM

“…First of all, a Braille recognition task was tried [5]. Even though only four kinds of city names were adopted, good performance on temporal signal processing for both temporal elasticity and spatial displacement was conårmed.…”

“…Following to the above-mentioned trend in temporal signal processing by SOM architecture, an Elman-type feedback SOM (EFSOM) was proposed [5]. It was applied to various kinds of tasks, including a Braille recognition task [5], an on-line character recognition task [6], [7] and so on, and it showed good performance on temporal signal processing for both temporal elasticity and spatial displacement.…”

“…It was applied to various kinds of tasks, including a Braille recognition task [5], an on-line character recognition task [6], [7] and so on, and it showed good performance on temporal signal processing for both temporal elasticity and spatial displacement.…”

Cellular Neural Network for Associative Memory and Its Application to Braille Image Recognition

“…Some studies that neural networks was applied to Braille recognition have been reported. In [2], Braille documents read by tactile were considered as time series information, and a new SOM architecture with feedback connections was proposed. In [3], hierarchical neural network has been applied to Japanese Braille transcription, and its accuracy was improved.…”

“…CNN has some remarkable features:(1) CNN can be arranged in matrix and implemented by a simple analog circuit called a cell. (2) Each cell in CNN is connected to its neighbors only. Hence, its computation efficiency is superior to that of fullconnected neural network such as Hopfield model.…”