activity
20022014
most citedStatistical mechanics of lossy data compression using a non-monotonic perceptron

45 citations · 77 across the 6 of their papers we have counts for

collaborators

6 papers

cs.AI2014★ 3 cited

Chases and Escapes, and Optimization Problems

Toru Ohira

We propose a new approach for solving combinatorial optimization problem by utilizing the mechanism of chases and escapes, which has a long history in mathematics. In addition to t…

cond-mat.other2006★ 3 cited

Delayed Random Walks and Control

Tadaaki Hosaka, Toru Ohira

Issues of resonance that appear in non-standard random walk models are discussed. The first walk is called repulsive delayed random walk, which is described in the context of a sti…

cond-mat.other2006★ 13 cited

Balancing with Noise and Delay

Tadaaki Hosaka, Toru Ohira, Christian Luciani +2

Motivated by recent studies in human balance control, we study a delayed random walk with an unstable fixed point. It is observed that the random walker moves away from the unstabl…

cs.IT2005★ 13 cited

Statistical Mechanical Approach to Lossy Data Compression:Theory and Practice

Tadaaki Hosaka, Yoshiyuki Kabashima

The encoder and decoder for lossy data compression of binary memoryless sources are developed on the basis of a specific-type nonmonotonic perceptron. Statistical mechanical analys…

cond-mat.stat-mech2003

Statistical Mechanical Approach to Error Exponents of Lossy Data Compression

Tadaaki Hosaka, Yoshiyuki Kabashima

We present herein a scheme by which to accurately evaluate the error exponents of a lossy data compression problem, which characterize average probabilities over a code ensemble of…

cond-mat.stat-mech2002★ 45 cited

Statistical mechanics of lossy data compression using a non-monotonic perceptron

T. Hosaka, Y. Kabashima, H. Nishimori

The performance of a lossy data compression scheme for uniformly biased Boolean messages is investigated via methods of statistical mechanics. Inspired by a formal similarity to th…