Visual pattern recognition network: Its training algorithm and its optoelectronic architecture

A visual pattern recognition network and its training algorithm are proposed. The network constructed of a one-layer morphology network and a two-layer modified Hamming net. This visual network can implement invariant pattern recognition with respect to image translation and size projection. After supervised learning takes place, the visual network extracts image features and classifies patterns much the same as living beings do. Moreover we set up its optoelectronic architecture for real-time pattern recognition. (C) 1996 Optical Society of America

Pentylenetetrazole-induced status epilepticus following training does not impair expression of morphine-induced conditioned place preference

Learning and memory play an important role in morphine addiction. Status epilepticus (SE) can impair the spatial and emotional learning and memory. However, little is known about the effects of SE on morphine-induced conditioned place preference (CPP). Th

Partially Supervised Neighbor Embedding for Example-Based Image Super-Resolution

Neighbor embedding algorithm has been widely used in example-based super-resolution reconstruction from a single frame, which makes the assumption that neighbor patches embedded are contained in a single manifold. However, it is not always true for complicated texture structure. In this paper, we believe that textures may be contained in multiple manifolds, corresponding to classes. Under this assumption, we present a novel example-based image super-resolution reconstruction algorithm with clustering and supervised neighbor embedding (CSNE). First, a class predictor for low-resolution (LR) patches is learnt by an unsupervised Gaussian mixture model. Then by utilizing class label information of each patch, a supervised neighbor embedding is used to estimate high-resolution (HR) patches corresponding to LR patches. The experimental results show that the proposed method can achieve a better recovery of LR comparing with other simple schemes using neighbor embedding.

Supervised Gaussian Process Latent Variable Model for Dimensionality Reduction

The Gaussian process latent variable model (GP-LVM) has been identified to be an effective probabilistic approach for dimensionality reduction because it can obtain a low-dimensional manifold of a data set in an unsupervised fashion. Consequently, the GP-LVM is insufficient for supervised learning tasks (e. g., classification and regression) because it ignores the class label information for dimensionality reduction. In this paper, a supervised GP-LVM is developed for supervised learning tasks, and the maximum a posteriori algorithm is introduced to estimate positions of all samples in the latent variable space. We present experimental evidences suggesting that the supervised GP-LVM is able to use the class label information effectively, and thus, it outperforms the GP-LVM and the discriminative extension of the GP-LVM consistently. The comparison with some supervised classification methods, such as Gaussian process classification and support vector machines, is also given to illustrate the advantage of the proposed method.

Impact of Brunswick river mouth training walls on adjacent beaches, Brunswick heads, New South Wales, Australia

River training walls have been built at scores of locations along the NSW coast and their impacts on shoreline change are still not fully understood. In this study, the Brunswick River entrance and adjacent beaches are selected for examination of the impact of the construction of major training walls. Thirteen sets of aerial photographs taken between 1947 and 1994 are used in a CIS approach to accurately determine tire shoreline Position, beach contours and sand volumes, and their changes in both time and space, and then to assess the contribution of both tire structures and natural hydrodynamic conditions to large scale (years-decades and kilometres) beach changes. The impact of the training walls can be divided into four stages: natural conditions prior to their construction (pre 1959), major downdrift erosion and updrift accretion during and. following the construction of the walls in 1959 similar to 1962 and 1966. diminishing impact of the walls between 1966 and 1987, and finally no apparent impact between 1987 similar to 1994. The impact extends horizontally about 8 km updrift and 17 km downdrift, and temporally up to 25 years..