In this paper, we propose a novel sparse signal recovery algorithm called the trainable iterative soft thresholding algorithm (TISTA). The proposed algorithm consists of two estimation units: a linear estimation unit and a minimum mean squared error (MMSE) estimator based shrinkage unit. The error variance required in the MMSE shrinkage unit is precisely estimated from a tentative estimate of the original signal. The remarkable feature of the proposed scheme is that TISTA includes adjustable variables that control step size and the error variance for the MMSE shrinkage function. The variables are adjusted by standard deep learning techniques. The number of trainable variables of TISTA is nearly equal to the number of iteration rounds and is much smaller than that of known learnable sparse signal recovery algorithms. This feature leads to highly stable and fast training processes of TISTA. Computer experiments show that TISTA is applicable to various classes of sensing matrices, such as Gaussian matrices, binary matrices, and matrices with large condition numbers. Numerical results also demonstrate that, in many cases, TISTA provides significantly faster convergence than approximate message passing (AMP) and the learned iterative shrinkage thresholding algorithm and also outperforms orthogonal AMP in the NMSE performance.

In the present paper, we propose a novel sparse signal recovery algorithm called the Trainable Iterative Soft Thresholding Algorithm (TISTA). The proposed algorithm consists of two estimation units: a linear estimation unit and a minimum mean squared error (MMSE) estimator-based shrinkage unit. The estimated error variance required in the MMSE shrinkage unit is precisely estimated from a tentative estimate of the original signal. The remarkable feature of the proposed scheme is that TISTA includes adjustable variables that control step size and the error variance for the MMSE shrinkage. The variables are adjusted by standard deep learning techniques. The number of trainable variables of TISTA is nearly equal to the number of iteration rounds and is much smaller than that of known learnable sparse signal recovery algorithms. This feature leads to highly stable and fast training processes of TISTA. Computer experiments show that TISTA is applicable to various classes of sensing matrices such as Gaussian matrices, binary matrices, and matrices with large condition numbers. Numerical results also demonstrate that, in many cases, TISTA provides significantly faster convergence than AMP and the Learned ISTA and also outperforms OAMP in the NMSE performance.

We found that activation of the prefrontal and temporal cortices is related to the proportion of automatic thoughts in the cognitive model of depression.

Results suggested the possibility that WF-CBGT may be a feasible and promising intervention for Japanese workers on leave due to depression regardless of cross-cultural differences, but that additional research examining effectiveness using controlled designs and other samples is needed. Future research should examine the efficacy of this programme more systematically to provide relevant data to aid in the continued development of an evidence-based intervention.

Problematic pornography use (PPU) is the inability to control the use of pornography and is considered a form of compulsive sexual behavior. It can have a negative effect on one's life and is an important clinical and social issue. In Japan, there is no assessment tool to measure PPU and very little research has been done. The Problematic Pornography Use Scale is one of the scales assessing the severity of PPU. This study validated a Japanese version of the Problematic Pornography Use Scale (PPUS-J) and examined its psychometric properties in a sample of 1011 individuals through an online survey (502 men, 509 women; M age = 35.9 years, SD = 13.75). The results of the confirmatory factor analysis indicated that the four factors in the original scale were consistent with the factors in the PPUS-J, and strict invariance could be assumed for male and female participants. With regard to reliability, internal consistency indices were appropriate both at the overall and subscale levels for male and female participants. The PPUS-J showed good convergent and divergent validity due to the relationship between the subscales and other measures such as the Sexual Compulsivity Scale. These results demonstrate the validity of the PPUS-J for assessing problematic pornography use in a Japanese sample. Given the paucity of studies conducted in non-Western cultures and on women, this study will be useful in advancing research on PPU across different cultures. Future studies should examine test-retest reliability of the PPUS-J and its use with clinical groups.