A Meta-Cognitive Learning Algorithm for an Extreme Learning Machine Classifier

Ramasamy, Savitha; Sundaram, Suresh; Kim, H. J.

doi:10.1007/s12559-013-9223-2

Cited by 75 publications

(43 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relating the definition which "computing" was the processing of information, so each processing of single cognitive data was cognitive sub-computing and the processing of all cognitive data was cognitive computing. Cognitive computing was scientific means that expressed cognition, found the law of cognition, and explored the mysteries of the mankind mind [2]. Potential), PET (Positron Emission Tomography), fMRI (Functional Magnetic Resonance Imaging) [6].…”

Section: Introductionmentioning

confidence: 99%

Research of Single Unit Fuzzy Event Cognitive Computing Based on Goal

Kang¹,

Shi²

2016

Proceedings of the 2016 International Conference on Computer Science and Electronic Technology

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Research of Single Unit Fuzzy Event Cognitive Computing Based on Goal

Kang¹,

Shi²

2016

Proceedings of the 2016 International Conference on Computer Science and Electronic Technology

View full text Add to dashboard Cite

“…It also has an extremely fast learning speed compared with traditional gradient-based algorithms. Furthermore, ELM technique successfully overcomes the difficulty of the curse of dimensionality [2,3]. Currently, the application scope of ELMs covers face recognition [4,5], action recognition [6], video concept detection [7], and so on.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Texture Video Classification Using Extreme Learning Machine

Wang¹,

Liu²,

Sun³

2015

Proceedings in Adaptation, Learning and Optimization

View full text Add to dashboard Cite

Abstract. Recognition of complex dynamic texture is a challenging problem and captures the attention of the computer vision community for several decades. Essentially the dynamic texture recognition is a multiclass classification problem that has become a real challenge for computer vision and machine learning techniques. Existing classifier such as extreme learning machine cannot effectively deal with this problem, due to the reason that the dynamic textures belong to non-Euclidean manifold. In this paper, we propose a new approach to tackle the dynamic texture recognition problem. First, we utilize the affinity propagation clustering technology to design a codebook, and then construct a soft coding feature to represent the whole dynamic texture sequence. This new coding strategy preserves spatial and temporal characteristics of dynamic texture. Finally, by evaluating the proposed approach on the DynTex dataset, we show the effectiveness of the proposed strategy.

show abstract

“…1)McELM (Savitha et al, 2014) is an approach to handle multi class and imbalanced data stream. It has a meta-cognitive component which decides what sample of the training set is useful in building the model.…”

Section: Experimental Comparsion With Other Methodsmentioning

confidence: 99%

“…McELM (Savitha, Suresh, & Kim, 2014 the current sample is used to update the output weights of the cognitive component.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A reduced labeled samples (RLS) framework for classification of imbalanced concept-drifting streaming data.

Arabmakki¹

View full text Add to dashboard Cite

A Meta-Cognitive Learning Algorithm for an Extreme Learning Machine Classifier

Cited by 75 publications

References 37 publications

Research of Single Unit Fuzzy Event Cognitive Computing Based on Goal

Research of Single Unit Fuzzy Event Cognitive Computing Based on Goal

Dynamic Texture Video Classification Using Extreme Learning Machine

A reduced labeled samples (RLS) framework for classification of imbalanced concept-drifting streaming data.

Contact Info

Product

Resources

About