Many areas of science

ted in the first stage of retinal processing, the photoreceptor layer. In this work we measure the spectral distributions of light present in natural images by using a hyperspectral camera, 12--15 which provides a complete spectrum at each pixel. We derive human cone responses at each spatial location from the spectra, and from these we gather cone response statistics for analysis. This approach is related to that of Webster and Mollon, with the key difference that whereas they contrast the differences between various images, we study the ensemble statistics as averaged over images. Our results are qualitatively similar to those of Buchsbaum and Gottschalk, who sought to understand theoretically, by using model stimuli, how the visual system might decorrelate natural cone signals through an orthogonal linear transformation. They found that under certain conditions this can be achieved through a transformation to a luminancelike channel and a pair of blue-- yellow and red--gre

Abstract not found

Currently, there is a lack of general-purpose, in-place learning engines that incrementally learn multiple tasks, to develop “soft ” multi-task-shared invariances in the intermediate internal representation while a developmental robot interacts with its environment. In-place learning is a biologically inspired concept, rooted in the genomic equivalence principle, meaning that each neuron is responsible for its own development while interacting with its environment. With in-place learning, there is no need for a separate learning network. Computationally, biologically inspired, in-place learning provides unusually efficient learning algorithms whose simplicity, low computational complexity, and generality are set apart from typical conventional learning algorithms. We present in this paper the multiple-layer in-place learning network (MILN) for this ambitious goal. As a key requirement for autonomous mental development, the network enables both unsupervised and supervised learning to occur concurrently, depending on whether motor supervision signals are available or not at the motor end (the last layer) during the agent’s interactions with the environment. We present principles based on which MILN automatically develops invariant neurons in different layers and why such invariant neuronal clusters

Non-negative Matrix Factorization (NMF) is a part-based image representation method which adds a non-negativity constraint to matrix factorization. NMF is compatible with the intuitive notion of combining parts to form a whole face. In this paper, we propose a framework of face recognition by adding NMF constraint and classifier constraints to matrix factorization to get both intuitive features and good recognition results. Based on the framework, we present two novel subspace methods: Fisher Non-negative Matrix Factorization (FNMF) and PCA Non-negative Matrix Factorization (PNMF). FNMF adds both the non-negative constraint and the Fisher constraint to matrix factorization. The Fisher constraint maximizes the between-class scatter and minimizes the withinclass scatter of face samples. Subsequently, FNMF improves the capability of face recognition. PNMF adds the non-negative constraint and characteristics of PCA, such as maximizing the variance of output coordinates, orthogonal bases, etc. to matrix factorization. Therefore, we can get intuitive features and desirable PCA characteristics. Our experiments show that FNMF and PNMF achieve better face recognition performance than NMF and Local NMF.

Abstract: Quality monitoring and fault detection are essential parts in automated electronics manufacturing systems. Information about process conditions enables operations to improve quality and increase throughput. This report presents a general quality monitoring framework and method for a manufacturing system. Proposed monitoring approach is an integration of model-based methods with systematically collected expert knowledge and data. A model bank is constructed to reproduce behaviour of the normal and fault states. The data driven normal condition model contains linguistic equation- non-linear scaling method for model variables, and a recursive gradient algorithm. Fuzzy reasoning and basic statistical methods are combined to identify changes in normal model residuals. Fault models are fuzzy rules for detecting abnormalities in selected time series signal. Analysed model outputs are then applied to monitoring task. Principles of the monitoring method are briefly discussed and demonstrated with a simulation example. Modelling results indicate that the proposed method can handle noise in simulation data. Generalisation ability of the normal model was also notified. Based on simulations, presented monitoring approach was

Many problems in paleontology reduce to finding those features that best discriminate among a set of classes. A clear example is the classification of new specimens. However, these classifications are generally challenging because the number of discriminant features and the number of samples are limited. This has been the fate of LB1, a new specimen found in the Liang Bua Cave of Flores. Several authors have attributed LB1 to a new species of Homo, H. floresiensis. According to this hypothesis, LB1 is either a member of the early Homo group or a descendent of an ancestor of the Asian H. erectus. Detractors have put forward an alternate hypothesis, which stipulates that LB1 is in fact a microcephalic modern human. In this paper, we show how we can employ a new Bayes optimal discriminant feature extraction technique to help resolve this type of issues. In this process, we present three types of experiments. First, we use this Bayes optimal discriminant technique to develop a model of morphological (shape) evolution from Australopiths to H. sapiens. LB1 fits perfectly in this model as a member of the early Homo group. Second, we build a classifier based on the available cranial and mandibular data appropriately normalized for size and volume. Again, LB1 is most similar to early Homo. Third, we build a brain endocast classifier to show that LB1 is not within the normal range of variation in H. sapiens. These results combined support the hypothesis of a very early shared ancestor for LB1 and H. erectus, and illustrate how discriminant analysis approaches can be successfully used to help classify newly discovered specimens.

This paper presents a simple yet effective method to analyze process variations using statistics on manufacturing in-line data without assuming any explicit underlying model for process variations. Our method is based on a variant of principal component analysis and is able to reveal systematic variation patterns existing on a die-to-die and wafer-to-wafer level individually. The separation of die variation from wafer variation can enhance the understanding of a nature of the process uncertainty. Our case study based on the proposed decomposition method shows that the dominating die-todie variation and wafer-to-wafer variation represent 31% and 25 % of the total variance of a large set of in-line parameters in 65nm SOI CMOS technology. 1.

Abstract not found