Can competitive learning compete? Comparing a connectionist clustering technique to symbolic approaches

2002 ◽  
Author(s):  
J.J. Mahoney ◽  
R.J. Mooney
Keyword(s):  
Competitive Learning ◽  
Clustering Technique

IMPROVING STUDENTS ACHIEVEMENT IN VOCABULARY THROUGH LUSTERING TECHNIQUE

2013 ◽  
Vol 2 (2) ◽  
Author(s):  
Lisda Yuniati Tumanggor And Zainuddin
Keyword(s):  
Action Research ◽  
Learning Process ◽  
Quantitative Data ◽  
Teaching And Learning ◽  
Qualitative Data ◽  
Clustering Technique ◽  
Class Viii ◽  
The Subject ◽  
The Mean ◽  
Vocabulary Score

This study attempts to improve students’ vocabulary achievement through Clustering Technique. This study was conducted by using classroom action research. The subject of the research was class VIII-B SMP Katolik Trisakti 2 Medan that consisted of 32 students. The research was conducted in two cycles and each cycle consisted of three meetings. The instruments for collecting data were vocabulary tests for quantitative data and diary notes, observation sheet and questionnaire sheet for qualitative data. Students’ score kept improving in every test. In the first cycle test, the mean of vocabulary score was 64.68. And in the second cycle test, the mean of vocabulary score was 79.85. Based on diary notes, observation sheet and questionnaire sheet, teaching and learning process had done effectively showed the improvement. Every student was studied actively. And from the research can be concluded that Clustering Technique can improve students’ achievement in vocabulary.

scholarly journals A multilevel clustering technique for community detection

2021 ◽  
Vol 441 ◽  
pp. 64-78
Author(s):  
Isa Inuwa-Dutse ◽  
Mark Liptrott ◽  
Ioannis Korkontzelos
Keyword(s):  
Community Detection ◽  
Clustering Technique

scholarly journals The Role of Weight Normalization in Competitive Learning

1994 ◽  
Vol 6 (2) ◽  
pp. 255-269 ◽  
Author(s):  
Geoffrey J. Goodhill ◽  
Harry G. Barrow
Keyword(s):  
Learning Rule ◽  
Competitive Learning ◽  
Fixed Amount

The effect of different kinds of weight normalization on the outcome of a simple competitive learning rule is analyzed. It is shown that there are important differences in the representation formed depending on whether the constraint is enforced by dividing each weight by the same amount (“divisive enforcement”) or subtracting a fixed amount from each weight (“subtractive enforcement”). For the divisive cases weight vectors spread out over the space so as to evenly represent “typical” inputs, whereas for the subtractive cases the weight vectors tend to the axes of the space, so as to represent “extreme” inputs. The consequences of these differences are examined.

Sign in / Sign up

Export Citation Format

Share Document