The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have bean receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.

Multitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. It does this by learning tasks in parallel while using a shared representation; what is learned for each task can help other tasks be learned better. This paper reviews prior work on MTL, presents new evidence that MTL in backprop nets discovers task relatedness without the need of supervisory signals, and presents new results for MTL with k-nearest neighbor and kernel regression. In this paper we demonstrate multitask learning in three domains. We explain how multitask learning works, and show that there are many opportunities for multitask learning in real domains. We present an algorithm and results for multitask learning with case-based methods like k-nearest neighbor and kernel regression, and sketch an algorithm for multitask learning in decision trees. Because multitask learning works, can be applied to many different kinds of domains, and can be used with different learning algorithms, we conjecture there will be many opportunities for its use on real-world problems.

Visualization has proven to be a powerful and widely-applicable tool for the analysis and interpretation of multi-variate data. Most visualization algorithms aim to find a projection from the data space down to a two-dimensional visualization space. However, for complex data sets living in a high-dimensional space it is unlikely that a single two-dimensional projection can reveal all of the interesting structure. We therefore introduce a hierarchical visualization algorithm which allows the complete data set to be visualized at the top level, with clusters and sub-clusters of data points visualized at deeper levels. The algorithm is based on a hierarchical mixture of latent variable models, whose parameters are estimated using the expectation-maximization algorithm. We demonstrate the principle of the approach on a toy data set, and we then apply the algorithm to the visualization of a synthetic data set in 12 dimensions obtained from a simulation of multi-phase flows in oil pipelines,...

Abstract—This paper describes a new approach to matching geometric structure in 2D point-sets. The novel feature is to unify the tasks of estimating transformation geometry and identifying point-correspondence matches. Unification is realized by constructing a mixture model over the bipartite graph representing the correspondence match and by affecting optimization using the EM algorithm. According to our EM framework, the probabilities of structural correspondence gate contributions to the expected likelihood function used to estimate maximum likelihood transformation parameters. These gating probabilities measure the consistency of the matched neighborhoods in the graphs. The recovery of transformational geometry and hard correspondence matches are interleaved and are realized by applying coupled update operations to the expected log-likelihood function. In this way, the two processes bootstrap one another. This provides a means of rejecting structural outliers. We evaluate the technique on two real-world problems. The first involves the matching of different perspective views of 3.5-inch floppy discs. The second example is furnished by the matching of a digital map against aerial images that are subject to severe barrel distortion due to a line-scan sampling process. We complement these experiments with a sensitivity study based on synthetic data.

AbstractÐIn the absence of cues for absolute depth measurements as binocular disparity, motion, or defocus, the absolute distance between the observer and a scene cannot be measured. The interpretation of shading, edges, and junctions may provide a 3D model of the scene but it will not provide information about the actual ªscaleº of the space. One possible source of information for absolute depth estimation is the image size of known objects. However, object recognition, under unconstrained conditions, remains difficult and unreliable for current computational approaches. Here, we propose a source of information for absolute depth estimation based on the whole scene structure that does not rely on specific objects. We demonstrate that, by recognizing the properties of the structures present in the image, we can infer the scale of the scene and, therefore, its absolute mean depth. We illustrate the interest in computing the mean depth of the scene with application to scene recognition and object detection. Index TermsÐDepth, image statistics, scene structure, scene recognition, scale selection, monocular vision. 1

Properties of the human embodiment -- sensorimotor apparatus and neurological structure -- participate directly in the growth and development of cognitive processes against enormous worst case complexity. It is our position that relationships between morphology and perception over time lead to increasingly comprehensive models that describe the agent's relationship to the world. We are applying insight derived from neuroscience, neurology, and developmental psychology to the design of advanced robot architectures. To investigate developmental processes, we have begun to approximate the human sensorimotor configuration and to engage sensory and motor subsystems in developmental sequences. Many such sequences have been documented in studies of infant development, so we intend to bootstrap cognitive structures in robots by emulating some of these growth processes that bear an essential resemblance to the human morphology. In this paper, we will show two related examples in which a humanoid robot determines the models and representations that govern its behavior. The first is a model that captures the dynamics of a haptic exploration of an object with a dextrous robot hand that supports skillful grasping. The second example constructs constellations of visual features to predict relative hand/object postures that lead reliably to haptic utility. The result is a rst step in a trajectory toward associative visual-haptic categories that bounds the incremental complexity of each stage of development.

Existing statistical approaches to natural language problems are very coarse approximations to the true complexity of language processing.

A method for incorporating context-dependent phone classes in a connectionist-HMM hybrid speech recognition system is introduced. A modular approach is adopted, where single-layer networks discriminate between different context classes given the phone class and the acoustic data. The context networks are combined with a context-independent (CI) network to generate context-dependent (CD) phone probability estimates. Experiments show an average reduction in word error rate of 16% and 13% from the CI system on ARPA 5,000 word and SQALE 20,000 word tasks respectively. Due to improved modelling, the decoding speed of the CD system is more than twice as fast as the CI system. INTRODUCTION The abbot hybrid connectionist-HMM system performed competitively with many conventional hidden Markov model (HMM) systems in the 1994 ARPA evaluations of speech recognition systems (Hochberg, Cook, Renals, Robinson & Schechtman 1995). This hybrid framework is attractive because it is compact, having far f...

Evolutionary computation (EC) consists of the design and analysis of probabilistic algorithms inspired by the principles of natural selection and variation. Genetic Programming (GP) is one subfield of EC that emphasizes desirable features such as the use of procedural representations, the capability to discover and exploit intrinsic characteristics of the application domain, and the flexibility to adapt the shape and complexity of learned models. Approaches that learn monolithic representations are considerably less likely to be effective for complex problems, and standard GP is no exception. The main goal of this dissertation is to extend GP capabilities with automatic mechanisms to cope with problems of increasing complexity. Humans succeed here by skillfully using hierarchical decomposition and abstraction mechanisms. The translation of such mechanisms into a general computer implementation is a tremendous challenge, which requires a firm understanding of the interplay between repr...

Abstract not found