Yoshiyuki Kabashima

Yoshiyuki Kabashima

Auto-generated profile, based on publicly available information

Yoshiyuki Kabashima

The University of Tokyo

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 October 2003 in Journal of Physics A: General Physics
Verified
Journal Article
Closed access
PDF file
YKYoshiyuki Kabashima
Yoshiyuki Kabashima

1 December 2006 in Europhysics Letters
Verified
Journal Article
Closed access
PDF file
KTK. Takeda
K. Takeda
SUS. Uda
S. Uda
YKY. Kabashima
Y. Kabashima
An approach to analyze the performance of the code division multiple access (CDMA) scheme, which is a core technology used in modern wireless communication systems, is provided. The approach characterizes the objective system by the eigenvalue spectrum of a cross-correlation matrix composed of signature sequences used in CDMA communication, which enable us to handle a wider class of CDMA systems beyond the basic model reported by Tanaka in Europhys. Lett., 54 (2001) 540. The utility of the scheme is shown by analyzing a system in which the generation of signature sequences is designed for enhancing the orthogonality.

17 November 2014 in Physical Review E
Verified
Journal Article
Closed access
PDF file
HHHaiping Huang
Haiping Huang
YKYoshiyuki Kabashima
Yoshiyuki Kabashima
Through supervised learning in a binary perceptron one is able to classify an extensive number of random patterns by a proper assignment of binary synaptic weights. However, to find such assignments in practice is quite a nontrivial task. The relation between the weight space structure and the algorithmic hardness has not yet been fully understood. To this end, we analytically derive the Franz-Parisi potential for the binary perceptron problem by starting from an equilibrium solution of weights and exploring the weight space structure around it. Our result reveals the geometrical organization of the weight space; the weight space is composed of isolated solutions, rather than clusters of exponentially many close-by solutions. The pointlike clusters far apart from each other in the weight space explain the previously observed glassy behavior of stochastic local search heuristics.

1 January 2008 in Journal of Physics: Conference Series
Verified
Conference Paper
Closed access
YKY Kabashima
Y Kabashima
A framework to analyze inference performance in densely connected single-layer feed-forward networks is developed for situations where a given data set is composed of correlated patterns. The framework is based on the assumption that the left and right singular value bases of the given pattern matrix are generated independently and uniformly from Haar measures. This assumption makes it possible to characterize the objective system by a single function of two variables which is determined by the eigenvalue spectrum of the cross-correlation matrix of the pattern matrix. Links to existing methods for analysis of perceptron learning and Gaussian linear vector channels and an application to a simple but nontrivial problem are also shown.

1 May 2016 in Journal of Statistical Mechanics: Theory and Experiment
Verified
Journal Article
Open access
PDF file
TOTomoyuki Obuchi
Tomoyuki Obuchi
YKYoshiyuki Kabashima
Yoshiyuki Kabashima

23 August 2013 in Journal of Physics A: Mathematical and Theoretical
Verified
Journal Article
Closed access
HHHaiping Huang
Haiping Huang
KWK Y Michael Wong
K Y Michael Wong
YKYoshiyuki Kabashima
Yoshiyuki Kabashima