Dynamic self-organising map

Rougier, Nicolas P.; Boniface, Yann

doi:10.1016/j.neucom.2010.06.034

Cited by 60 publications

(68 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering the medical datasets is difficult because of limited observation, information, diagnosis and prognosis of the specialist; incomplete medical knowledge; and lack of enough time for diagnosis [37]. However, the developed SFFNN method has the capability to overcome some of the problems associated with clustering in the prediction of survival time of the breast cancer patients from the UMMC.…”

Section: Discussionmentioning

confidence: 99%

“…labels, control noisy data, cluster unknown data, and learn the types of input values on the basis of their weights and properties [6,9,[12][13][14]. UFFNN clustering methods often use Hebbian learning, competitive learning, or competitive Hebbian learning.…”

mentioning

confidence: 99%

“…Clustering of some kinds of data is so difficult because of their character and structure. For example, clustering the medical data sets is difficult because of limited observation, information, diagnosis and prognosis of the specialist; incomplete medical knowledge; and lack of enough time for diagnosis [37]. The current UFFNN clustering methods generally use random weights, thresholds and parameters for controlling tasks during clustering, such as the SOM that creates the code book of weights by selection of the input data randomly.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Single-Layer Semi-Supervised Feed Forward Neural Network Clustering Method

Asadi

Kareem

Asadi

et al. 2015

MJCS

View full text Add to dashboard Cite

The aim of this research is to develop and propose a single-layer semi-supervised feed forward neural network clustering method with one epoch training in order to solve the problems of low training speed, accuracy and high time and memory complexities of clustering. A code book of non-random weights is learned through the input data directly. Then, the best match weight (BMW) vector is mined from the code book, and consequently an exclusive total threshold of each input data is calculated based on the BMW vector. The input data are clustered based on their exclusive total thresholds. Finally, the method assigns a class label to each input data by using a K-step activation function for comparing the total thresholds of the training set and the test set. The class label of other unlabeled and unknown input test data are predicted based on their clusters or trial and

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A Single-Layer Semi-Supervised Feed Forward Neural Network Clustering Method

Asadi

Kareem

Asadi

et al. 2015

MJCS

View full text Add to dashboard Cite

show abstract

“…In their experiment, the robot progressed through a staged development whereby eye saccades emerged first, followed by gaze control, then primitive reaching, and followed by eventual coordinated gaze-to-touch behaviors. An extension of the approach proposed by Kajić et al (2014) was presented by Schillaci et al (2014), where Dynamic Self-Organizing Maps [DSOMs (Rougier and Boniface, 2011)] and a Hebbian paradigm were adopted for online and continuous learning on both static and dynamic data distributions. The authors addressed the learning of visuo-motor coordination in robots, but focused on the capability of the proposed internal model for body representations to adapt to sudden changes in the dynamics of the system.…”

Section: Internal Body Representationsmentioning

confidence: 99%

Exploration Behaviors, Body Representations, and Simulation Processes for the Development of Cognition in Artificial Agents

2016

View full text Add to dashboard Cite

Sensorimotor control and learning are fundamental prerequisites for cognitive development in humans and animals. Evidence from behavioral sciences and neuroscience suggests that motor and brain development are strongly intertwined with the experiential process of exploration, where internal body representations are formed and maintained over time. In order to guide our movements, our brain must hold an internal model of our body and constantly monitor its configuration state. How can sensorimotor control enable the development of more complex cognitive and motor capabilities? Although a clear answer has still not been found for this question, several studies suggest that processes of mental simulation of action-perception loops are likely to be executed in our brain and are dependent on internal body representations. Therefore, the capability to re-enact sensorimotor experience might represent a key mechanism behind the implementation of higher cognitive capabilities, such as behavior recognition, arbitration and imitation, sense of agency, and self-other distinction. This work is mainly addressed to researchers in autonomous motor and mental development for artificial agents. In particular, it aims at gathering the latest developments in the studies on exploration behaviors, internal body representations, and processes of sensorimotor simulations. Relevant studies in human and animal sciences are discussed and a parallel to similar investigations in robotics is presented.

show abstract

“…1. Perceptions of the robot (we give more details on these perceptions in Section 4), denoted s, feed a Dynamic Self-Organizing Map (DSOM) [Rougier and Boniface, 2011]. The activity of this self-organizing map is the input of a perceptron with one layer of neurons that has as many outputs as possible actions.…”

Section: Architecture For Developmental Learningmentioning

confidence: 99%