Details

Autor(en) / Beteiligte

• Kamimura, Ryotaro
• Yoshida, Fumihiko
• Kitajima, Ryozo

Titel

Collective Information-Theoretic Competitive Learning: Emergency of Improved Performance by Collectively Treated Neurons

Ist Teil von

• Lecture notes in computer science, 2006, p.626-633

Ort / Verlag

Berlin, Heidelberg: Springer Berlin Heidelberg

Erscheinungsjahr

2006

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• In this paper, we try to show that the simple collection of competitive units can show some emergent property such as improved generalization performance. We have so far defined information-theoretic competitive learning with respect to individual competitive units. As information is increased, one competitive unit tends to win the competition. This means that competitive learning can be described as a process of information maximization. However, in living systems, a large number of neurons behave collectively. Thus, it is urgently needed to introduce collective property in information-theoretic competitive learning. In this context, we try to treat several competitive units as one unit, that is, one collective unit. Then, we try to maximize information content not in individual competitive units but in collective competitive units. We applied the method to an artificial data and cabinet approval rating estimation. In all cases, we successfully demonstrated that improved generalization could be obtained.