Feedback Self-Organizing Map and Its Application to Spatio-Temporal Pattern Classification

Horio, Keiichi; Yamakawa, Takeshi

doi:10.1142/s1469026801000081

Cited by 29 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And, in order to represent secondary candidates and a quantitative measure of confidence of applied input signals, another output layer is provided next to the competitive layer. Each of these structures has been proposed independently as a feedback SOM (FSOM) [4] and an MCP network [10], so we construct a new type of network taking into account their advantages. The proposed model consists of four layers, an input layer x, a competitive layer y, a state layer h, and an output layer z.…”

Section: An Elman-type Feedback Sommentioning

confidence: 99%

“…Another method is to replace conventional neurons in the standard SOM with dynamic elements [2,3]. Making use of feedback pathways to return the output signal to the input nodes as a part of the net input signal at the next time frame [4] is also effective. A survey of these approaches makes us realize that it resembles the stream developing from multilayer neural networks, as for the SOMs which do not possess dynamics intrinsically, to recurrent networks including time-delay neural networks (TDNNs) [5], finite impulse response (FIR) networks [6], Kleinfeld's model [7], Jordan's model [8], and Elman's model [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Wakuya

Harada

Shida

2007

Systems & Computers in Japan

View full text Add to dashboard Cite

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.

show abstract

Section: An Elman-type Feedback Sommentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Wakuya

Harada

Shida

2007

Systems & Computers in Japan

View full text Add to dashboard Cite

show abstract

“…Although it was proposed as one of neural network models for the biological visual information processing system originally, a topology-preserving projection from the input layer (the multi-dimensional space) to the competitive layer (the two-dimensional plane) developed through training is quite attractive. From the viewpoint of fundamental studies, several new architectures have been proposed (Yamakawa and Horio 1999;Horio and Yamakawa 2001;Tokunaga et al 2003), and they are applied to various kinds of practical tasks for associative memory, systems control, temporal signal processing, pattern generation, and so on (Sakurai et al 2002;Sudo et al 2007;Ishiguma and Wakuya 2007;Wakuya et al 2012;Yamaguchi 2013;Miyakoda and Inoue 2014).…”

Section: Introductionmentioning

confidence: 99%

An analysis of multi-dimensional data containing emphasized items by self-organizing map and its application to sightseeing information analysis

et al. 2016

View full text Add to dashboard Cite

One of the attractive features which a selforganizing map (SOM) possesses is a topology-preserving projection from the input layer to the competitive layer. Generally speaking, its correspondence is developed through training based on information representations of the applied multi-dimensional data. A developed feature map in the competitive layer enables us easy to understand some underlying rules visually. By the way, an analysis of Saga Prefectural sightseeing information by a SOM has been tried so far. According to the results of preceding studies, applied various topics are divided into several groups successfully. Nevertheless, there are some items not reflected in them at all. This fact implies that representations of the applied data are not appropriate to develop the feature map which we have intended in advance. Then, to overcome this tough problem, a simple idea to emphasize particular items depending on our interests is introduced as pre-synaptic processing. As a result of some computer simulations, it is confirmed that the developed feature maps are modified adaptively depending Communicated by on the emphasized coefficient. And, it is concluded that the proposed simple method is effective.

show abstract

“…Modified versions of SOM that have enjoyed a great deal of interest equip SOM with additional feed-back connections that allow for natural processing of recursive data types. Typical examples of such models are Temporal Kohonen Map [5], recurrent SOM [6], feedback SOM [7], recursive SOM [1], merge SOM [8] and SOM for structured data [9]. However, the representational capabilities and internal representations of the models are not well understood [3,10,11].…”

Section: Introductionmentioning

confidence: 99%

Recursive Self-organizing Map as a Contractive Iterative Function System

Tiňo

Farkaš

Mourik

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Recently, there has been a considerable research activity in extending topographic maps of vectorial data to more general data structures, such as sequences or trees. However, the representational capabilities and internal representations of the models are not well understood. We rigorously analyze a generalization of the Self-Organizing Map (SOM) for processing sequential data, Recursive SOM (RecSOM [1]), as a non-autonomous dynamical system consisting of a set of fixed input maps. We show that contractive fixed input maps are likely to produce Markovian organizations of receptive fields on the RecSOM map. We derive bounds on parameter β (weighting the importance of importing past information when processing sequences) under which contractiveness of the fixed input maps is guaranteed.

show abstract

Feedback Self-Organizing Map and Its Application to Spatio-Temporal Pattern Classification

Cited by 29 publications

References 9 publications

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

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

An analysis of multi-dimensional data containing emphasized items by self-organizing map and its application to sightseeing information analysis

Recursive Self-organizing Map as a Contractive Iterative Function System

Contact Info

Product

Resources

About