Couple discord and depression in couples during couple therapy and in depressed individuals during depression treatment.

The association between depression and relationship distress as well as the impact of treatment for the one on the other was examined across 2 treatment-seeking samples: individuals seeking treatment for depression (N = 120) and couples seeking marital therapy (N = 134 couples). Although there was a baseline association between depression and distress across the 2 samples, relationship distress was far more prevalent among those being treated for depression than was depression for those seeking marital therapy. There was a reliable association between changes in the primary problem (e.g., relationship distress in the couple therapy study) and changes in the secondary problem (e.g., depression in the couple therapy study). However, overall effects on secondary problems were quite small. Neuroticism played a complex, moderating role across the 2 samples, strengthening and weakening the association between depression and relationship distress depending on the sample and gender, replicating previous findings. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Discriminant pattern recognition using transformation-invariant neurons

To overcome the problem of invariant pattern recognition, Simard, LeCun, and Denker (1993) proposed a successful nearest-neighbor approach based on tangent distance, attaining state-of-the-art accuracy. Since this approach needs great computational and memory effort, Hastie, Simard, and S?ckinger (1995) proposed an algorithm (HSS) based on singular value decomposition (SVD), for the generation of nondiscriminant tangent models. In this article we propose a different approach, based on a gradient-descent constructive algorithm, called TD-Neuron, that develops discriminant models. We present as well comparative results of our constructive algorithm versus HSS and learning vector quantization (LVQ) algorithms. Specifically, we tested the HSS algorithm using both the original version based on the two-sided tangent distance and a new version based on the one-sided tangent distance. Empirical results over the NIST-3 database show that the TD-Neuron is superior to both SVD- and LVQ-based algorithms, since it reaches a better trade-off between error and rejection.