activity
20022026
most citedTransient dynamics for sequence processing neural networks

31 citations · 77 across the 11 of their papers we have counts for

collaborators

11 papers

cond-mat.stat-mech2026

de Almeida-Thouless Stability and Replica Symmetry Breaking in a Hybrid Watermarking Model with Image and Message Decoding

Tatsuya Uezu, Kao Hayashi, Masaki Kawamura

We investigate the de Almeida-Thouless (AT) stability of the replica symmetric (RS) solution for a spread-spectrum watermarking model incorporating Bayes-estimation-based image res…

cs.CV2026

Estimation of geometric transformation matrices using grid-shaped pilot signals

Rinka Kawano, Masaki Kawamura

Digital watermarking techniques are essential to prevent unauthorized use of images. Since pirated images are often geometrically distorted by operations such as scaling and croppi…

cs.MM2024★ 1 cited

Performance Evaluation of Associative Watermarking Using Statistical Neurodynamics

Ryoto Kanegae, Masaki Kawamura

We theoretically evaluated the performance of our proposed associative watermarking method in which the watermark is not embedded directly into the image. We previously proposed a…

cond-mat.stat-mech2012★ 3 cited

Statistical mechanical evaluation of spread spectrum watermarking model with image restoration

Masaki Kawamura, Kao Hayashi, Tatsuya Uezu +1

In cases in which an original image is blind, a decoding method where both the image and the messages can be estimated simultaneously is desirable. We propose a spread spectrum wat…

cond-mat.dis-nn2007★ 4 cited

Retrieval of branching sequences in associative memory model with common external input and bias input

Kentaro Katahira, Masaki Kawamura, Kazuo Okanoya +1

We investigate a recurrent neural network model with common external and bias inputs that can retrieve branching sequences. Retrieval of memory sequences is one of the most importa…

cond-mat.dis-nn2006★ 6 cited

Stochastic transitions of attractors in associative memory models with correlated noise

Masaki Kawamura, Masato Okada

We investigate dynamics of recurrent neural networks with correlated noise to analyze the noise's effect. The mechanism of correlated firing has been analyzed in various models, bu…