Incremental Linear Discriminant Analysis Using Sufficient Spanning Sets and Its Applications

This paper presents an incremental learning solution for Linear Discriminant Analysis (LDA) and its applications to object recognition problems. We apply the sufficient spanning set approximation in three steps i.e. update for the total scatter matrix, between-class scatter matrix and the projected data matrix, which leads an online solution which closely agrees with the batch solution in accuracy while significantly reducing the computational complexity. The algorithm yields an efficient solution to incremental LDA even when the number of classes as well as the set size is large. The incremental LDA method has been also shown useful for semi-supervised online learning. Label propagation is done by integrating the incremental LDA into an EM framework. The method has been demonstrated in the task of merging large datasets which were collected during MPEG standardization for face image retrieval, face authentication using the BANCA dataset, and object categorisation using the Caltech101 dataset. © 2010 Springer Science+Business Media, LLC.

Gaussian Process Regression Networks

We introduce a new regression framework, Gaussian process regression networks (GPRN), which combines the structural properties of Bayesian neural networks with the non-parametric flexibility of Gaussian processes. This model accommodates input dependent signal and noise correlations between multiple response variables, input dependent length-scales and amplitudes, and heavy-tailed predictive distributions. We derive both efficient Markov chain Monte Carlo and variational Bayes inference procedures for this model. We apply GPRN as a multiple output regression and multivariate volatility model, demonstrating substantially improved performance over eight popular multiple output (multi-task) Gaussian process models and three multivariate volatility models on benchmark datasets, including a 1000 dimensional gene expression dataset.

Molecular basis of albinism in the rhesus monkey

Sequence analysis of the tyrosinase (TYR) coding region from one albino rhesus monkey (Macaca mulatta) family revealed that the two monkeys with phenotype similar to human TYR-negative oculocutaneous albinism (OCA) were homozygous for a missense mutation (S184TER) in exon 1 at codon 184. The offspring of one of the albino monkey (''Kangkang'') are all heterozygous for the S184TER mutation, but the S184TER mutation was not observed in 93 control individuals. We conclude that the point mutation is responsible and sufficient to generate the albino rhesus monkey phenotype. The rough age of the S184TER nonsense mutation may be about 0.8 million years using a rate of 0.16% per million years. (C) 2000 Elsevier Science B.V. All rights reserved.

Molecular genetic basis for the rhino mouse from Chinese KM subcolony

Both the rhino mouse and hairless mouse resulted from hairless gene mutation, but they show different phenotypes of skin physiology. The rhino mouse has more similar histological characters to human papular alopecia. Therefore rhino mouse is a good experimental animal model for human papular alopecia. This study reports a hairless mouse named rhino KIZ, arose from KM colony in Kunming Institue of Zoology, by systematic studies on morphology, skin histopathology, gene sequence, pedigree and protein domain analysis. The results demonstrate that a C-to-T transition in exon 11 of hr gene (The mutant gene has been applied for a Chinese patent (patent No. 03135280)) results in the rhino KIZ. The rhino KIZ with clear genetic mechanism will be a useful animal model.

Nearest neighbour decoding and pilot-aided channel estimation in stationary Gaussian flat-fading channels

We study the information rates of non-coherent, stationary, Gaussian, multiple-input multiple-output (MIMO) flat-fading channels that are achievable with nearest neighbour decoding and pilot-aided channel estimation. In particular, we analyse the behaviour of these achievable rates in the limit as the signal-to-noise ratio (SNR) tends to infinity. We demonstrate that nearest neighbour decoding and pilot-aided channel estimation achieves the capacity pre-logwhich is defined as the limiting ratio of the capacity to the logarithm of SNR as the SNR tends to infinityof non-coherent multiple-input single-output (MISO) flat-fading channels, and it achieves the best so far known lower bound on the capacity pre-log of non-coherent MIMO flat-fading channels. © 2011 IEEE.

Gaussian fading is the worst fading

The capacity of peak-power limited, single-antenna, noncoherent, flat-fading channels with memory is considered. The emphasis is on the capacity pre-log, i.e., on the limiting ratio of channel capacity to the logarithm of the signal-to-noise ratio (SNR), as the SNR tends to infinity. It is shown that, among all stationary and ergodic fading processes of a given spectral distribution function and whose law has no mass point at zero, the Gaussian process gives rise to the smallest pre-log. The assumption that the law of the fading process has no mass point at zero is essential in the sense that there exist stationary and ergodic fading processes whose law has a mass point at zero and that give rise to a smaller pre-log than the Gaussian process of equal spectral distribution function. An extension of these results to multiple-input single-output (MISO) fading channels with memory is also presented. © 2006 IEEE.

Gaussian fading is the worst fading

The capacity of peak-power limited, single-antenna, non-coherent, flat-fading channels with memory is considered. The emphasis is on the capacity pre-log, i.e., on the limiting ratio of channel capacity to the logarithm of the signal-to-noise ratio (SNR), as the SNR tends to infinity. It is shown that, among all stationary & ergodic fading processes of a given spectral distribution function whose law has no mass point at zero, the Gaussian process gives rise to the smallest pre-log. © 2006 IEEE.