Gender differences in social network characteristics and psychological well-being among Hong Kong Chinese: the role of future time perspective and adherence to Renqing.

Gender differences in social network characteristics are well documented in the literature. Socio-emotional selectivity theory emphasizes the importance of future time perception on selection of social partners whereas cultural studies stress the roles of Renqing (relationship orientation) on social interactions. This study examined the effects of future time perspective and adherence to Renqing on social network characteristics, and their associations with psychological well-being of 321 Chinese men and women, aged 28-91 years. Results showed that adherence to Renqing partially accounted for gender differences in the number of relatives, even after controlling for the effects of extraversion and structural factors. Moreover, women, but not men, with lower adherence to Renqing and more limited future time perspective were found to be happier when they had fewer close friends in their social networks.

Impact of job characteristics on psychological health of Chinese single working women.

This study aims at investigating the impact of individual and contextual job characteristics of control, psychological and physical demand, and security on psychological distress of 193 Chinese single working women in Hong Kong. The mediating role of job satisfaction in the job characteristics-distress relation is also assessed. Multiple regression analysis results show that job satisfaction mediates the effects of job control and security in predicting psychological distress; whereas psychological job demand has an independent effect on mental distress after considering the effect of job satisfaction. This main effect model indicates that psychological distress is best predicted by small company size, high psychological job demand, and low job satisfaction. Results from a separate regression analysis fails to support the overall combined effect of job demand-control on psychological distress. However, a significant physical job demand-control interaction effect on mental distress is noted, which reduces slightly after controlling the effect of job satisfaction.

Constructive algorithms for structure learning in feedforward neural networks for regression problems.

In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally until a satisfactory solution is found. By formulating the whole problem as a state-space search, we first describe the general issues in constructive algorithms, with special emphasis on the search strategy. A taxonomy, based on the differences in the state transition mapping, the training algorithm, and the network architecture, is then presented.

Objective functions for training new hidden units in constructive neural networks.

In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of objective functions the computation of which and the corresponding weight updates can be done in O(N) time, where N is the number of training patterns. Moreover, even though input weight freezing is applied during the process for computational efficiency, the convergence property of the constructive algorithms using these objective functions is still preserved. We also propose a few computational tricks that can be used to improve the optimization of the objective functions under practical situations. Their relative performance in a set of two-dimensional regression problems is also discussed.

Use of bias term in projection pursuit learning improves approximation and convergence properties.

In a regression problem, one is given a multidimensional random vector X, the components of which are called predictor variables, and a random variable, Y, called response. A regression surface describes a general relationship between X and Y. A nonparametric regression technique that has been successfully applied to high-dimensional data is projection pursuit regression (PPR). The regression surface is approximated by a sum of empirically determined univariate functions of linear combinations of the predictors. Projection pursuit learning (PPL) formulates PPR using a 2-layer feedforward neural network. The smoothers in PPR are nonparametric, whereas those in PPL are based on Hermite functions of some predefined highest order R. We demonstrate that PPL networks in the original form do not have the universal approximation property for any finite R, and thus cannot converge to the desired function even with an arbitrarily large number of hidden units. But, by including a bias term in each linear projection of the predictor variables, PPL networks can regain these capabilities, independent of the exact choice of R. Experimentally, it is shown in this paper that this modification increases the rate of convergence with respect to the number of hidden units, improves the generalization performance, and makes it less sensitive to the setting of R. Finally, we apply PPL to chaotic time series prediction, and obtain superior results compared with the cascade-correlation architecture.

On reducing learning time in context-dependent mappings.

An approach to overcoming the slow convergence problems often associated with learning complex nonlinear mappings is presented. The mappings are learned in a context-dependent manner so that complex problems are decomposed into simpler subproblems corresponding to different contexts. While no general conditions for determining applicability the method have been found, its power is illustrated through experiments in controlling simulated robot manipulators in two and three degrees of freedom. The experiments also indicate that the method shows promising scale-up properties.