Biomedical subjects

Seungjin Choi

Publications and source records attributed to Seungjin Choi.

3 recordsLinked to original sources

PubMed2006

Differential learning algorithms for decorrelation and independent component analysis.

Decorrelation and its higher-order generalization, independent component analysis (ICA), are fundamental and important tasks in unsupervised learning, that were studied mainly in the domain of Hebbian learning. In this paper we present a variation of the natural gradient ICA, differential ICA, where the learning relies on the concurrent change of output variables. We interpret the differential learning as the maximum likelihood estimation of parameters with latent variables represented by the random walk model. In such a framework, we derive the differential ICA algorithm and, in addition, we also present the differential decorrelation algorithm that is treated as a special instance of the differential ICA. Algorithm derivation and local stability analysis are given with some numerical experimental results.

Acoustic Stimulation↗

PubMed2002

Equivariant nonstationary source separation.

Most of source separation methods focus on stationary sources, so higher-order statistics is necessary for successful separation, unless sources are temporally correlated. For nonstationary sources, however, it was shown [Neural Networks 8 (1995) 411] that source separation could be achieved by second-order decorrelation. In this paper, we consider the cost function proposed by Matsuoka et al. [Neural Networks 8 (1995) 411] and derive natural gradient learning algorithms for both fully connected recurrent network and feedforward network. Since our algorithms employ the natural gradient method, they possess the equivariant property and find a steepest descent direction unlike the algorithm [Neural Networks 8 (1995) 411]. We also show that our algorithms are always locally stable, regardless of probability distributions of nonstationary sources.

Algorithms↗

PubMed2002

Perception of risk of developing diabetes in offspring of type 2 diabetic patients.

BACKGROUND: The risk of developing diabetes is high in the offspring of patients with type 2 diabetes. There have been no studies to assess the offspring's awareness of the risk of developing diabetes. The aim of this study was to investigate how the male offspring of type 2 diabetic patients assess their likelihood of developing diabetes. METHODS: One hundred and one non-diabetic men with one or both parents having type 2 diabetes, aged 19-28 years, were recruited. RESULTS: Thirty-nine subjects (38.6%) were concerned about diabetes and 85 (84.2%) considered diabetes a serious problem. However, only 10 (9.9%) thought they might develop diabetes and 9 (8.9%) had previously attended diabetes education programs with their parents. The educational level amongst the diabetic parents was the only independent predictor of perception of the increased risk. Age, body mass index, waist-to-hip ratio, educational level and the perception of diabetes as a serious problem were not associated with perception of the increased risk. CONCLUSION: Most offspring of diabetic parents lacked knowledge about the increased risk amongst family members. We suggest that physicians and diabetic educators should provide knowledge about the increased risk of developing diabetes in offspring and the benefit of lifestyle modification to delay or prevent the development of the disease.

Adult↗