Abstract not found

Statistical techniques based on hidden Markov Models (HMMs) with Gaussian emission densities have dominated signal processing and pattern recognition literature for the past 20 years. However, HMMs trained using maximum likelihood techniques suffer from an inability to learn discriminative information and are prone to overfitting and over-parameterization. Recent work in machine learning has focused on models, such as the support vector machine (SVM), that automatically control generalization and parameterization as part of the overall optimization process. In this paper, we show that SVMs provide a significant improvement in performance on a static pattern classification task based on the Deterding vowel data. We also describe an application of SVMs to large vocabulary speech recognition, and demonstrate an improvement in error rate on a continuous alphadigit task (OGI Aphadigits) and a large vocabulary conversational speech task (Switchboard). Issues related to the development and optimization of an SVM/HMM hybrid system are discussed.

Using neural nets to simulate learning and the genetic algorithm to simulate evolution in a toy world of mushrooms and mushroom-foragers, we place two ways of acquiring categories into direct competition with one another: In (1) "sensorimotor toil," new categories are acquired through real-time, feedbackcorrected, trial and error experience in sorting them. In (2) "symbolic theft," new categories are acquired by hearsay from propositions -- boolean combinations of symbols describing them. In competition, symbolic theft always beats sensorimotor toil. We hypothesize that this is the basis of the adaptive advantage of language. Entry-level categories must still be learned by toil, however, to avoid an infinite regress (the "symbol grounding problem"). Changes in the internal representations of categories must take place during the course of learning by toil. These changes can be analyzed in terms of the compression of within-category similarities and the expansion of between-...

This paper describes different types of models for the evolution of communication and language. It uses the distinction between signals, symbols, and words for the analysis of evolutionary models of language. In particular, it show how evolutionary computation techniques, such as Artificial Life, can be used to study the emergence of syntax and symbols from simple communication signals. Initially, a computational model that evolves repertoires of isolated signals is presented. This study has simulated the emergence of signals for naming foods in a population of foragers. This type of model studies communication systems based on simple signal-object associations. Subsequently, models that study the emergence of grounded symbols are discussed in general, including a detailed description of a work on the evolution of simple syntactic rules. This model focuses on the emergence of symbol-symbol relationships in evolved languages. Finally, computational models of syntax acquisition and evolution are discussed. These different types of computational models provide an operational def'mition of the signal/symbol/word distinction. The simulation and analysis of these types of models will help understanding the role of symbols and symbol acquisition in the origin of language.

Neural network models of categorical perception (compression of within-category similarity and dilation of between-category differences) are applied to the symbol-grounding problem (of how to connect symbols with meanings) by connecting analog sensorimotor projections to arbitrary symbolic representations via learned category-invariance detectors in a hybrid symbolic/nonsymbolic system. Our nets are trained to categorize and name 50x50 pixel images (e.g., circles, ellipses, squares and rectangles) projected onto the receptive field of a 7x7 retina. They first learn to do prototype matching and then entry-level naming for the four kinds of stimuli, grounding their names directly in the input patterns via hidden-unit representations ("sensorimotor toil"). We show that a higher-level categorization (e.g., "symmetric" vs. "asymmetric") can learned in two very different ways: either (1) directly from the input, just as with the entry-level categories (i.e., by toil), or (2) indirectly, from...

A hand-designed internal representation of the world cannot deal with unknown or uncontrolled environments. Motivated by human cognitive and behavioral development, this paper presents a theory, an architecture, and some experimental results for developmental robotics. By a developmental robot, we mean that the robot generates its “brain ” (or “central nervous system, ” including the information processor and controller) through online, real-time interactions with its environment (including humans). A new Self-Aware Self-Effecting (SASE) agent concept is proposed, based on our SAIL and Dav developmental robots. The manual and autonomous development paradigms are formulated along with a theory of representation suited for autonomous development. Unlike traditional robot learning, the tasks that a developmental robot ends up learning are unknown during the programming time so that the task-specific representation must be generated and updated through real-time “living ” experiences. Experimental results with SAIL and Dav developmental robots are presented, including visual attention selection, autonomous navigation, developmental speech learning, range-based obstacle avoidance, and scaffolding through transfer and chaining.

In this paper, we present a conceptual framework for indexing different aspects of visual information. Our framework unifies concepts from the literature in diverse fields such as cognitive psychology, library sciences, art, and the more recent contentbased retrieval. We present multiple level structures for visual and non-visual information. The ten-level visual structure presented provides a systematic way of indexing images based on syntax (e.g., color, texture, etc.) and semantics (e.g., objects, events, etc.), and includes distinctions between general concept and visual concept. We define different types of relations (e.g., syntactic, semantic) at different levels of the visual structure, and also use a semantic information table to summarize important aspects related to an image. While the focus is on the development of a conceptual indexing structure, our aim is also to bring together the knowledge from various fields, unifying the issues that should be considered when building ...

Searle's celebrated Chinese Room Argument has shaken the foundations of Artificial Intelligence. Many refutations have been attempted, but none seem convincing. This paper is an attempt to sort out explicitly the assumptions and the logical, methodological and empirical points of disagreement. Searle is shown to have underestimated some features of computer modeling, but the heart of the issue turns out to be an empirical question about the scope and limits of the purely symbolic (computational) model of the mind. Nonsymbolic modeling turns out to be immune to the Chinese Room Argument. The issues discussed include the Total Turing Test, modularity, neural modeling, robotics, causality and the symbol-grounding problem. 1.

& There are two competing theories of facial expression recognition. Some researchers have suggested that it is an example of ‘‘categorical perception.’ ’ In this view, expression categories are considered to be discrete entities with sharp boundaries, and discrimination of nearby pairs of expressive faces is enhanced near those boundaries. Other researchers, however, suggest that facial expression perception is more graded and that facial expressions are best thought of as points in a continuous, low-dimensional space, where, for instance, ‘‘surprise’ ’ expressions lie between ‘‘happiness’ ’ and ‘‘fear’’ expressions due to their perceptual similarity. In this article, we show that a simple yet biologically plausible neural network model, trained to classify facial expressions into six basic emotions, predicts data used to support both of these theories. Without any parameter tuning, the model matches a variety of psychological data on categorization, similarity, reaction times, discrimination, and recognition difficulty, both qualitatively and quantitatively. We thus explain many of the seemingly complex psychological phenomena related to facial expression perception as natural consequences of the tasks’ implementations in the brain. &

We present an automated emotion recognition system that is capable of identifying six basic emotions (happy, surprise, sad, angry, fear, disgust) in novel face images. An ensemble of simple feed-forward neural networks are used to rate each of the images. The outputs of these networks are then combined to generate a score for each emotion. The networks were trained on a database of face images that human subjects consistently rated as portraying a single emotion. Such a system achieves 86% generalization on novel face images (individuals the networks were not trained on) drawn from the same database. The neural network model exhibits categorical perception between some emotion pairs. A linear sequenceof morph images is created between two expressions of an individual's face and this sequence is analyzedby the model. Sharp transitions in the output response vector occur in a single step in the sequence for some emotion pairs and not for others. We plan to us the model's response to limi...