A computer program capable of acting intelligently in the world must have a general representation of the world in terms of which its inputs are interpreted. Designing such a program requires commitments about what knowledge

Recent neurological studies indicate that the role of emotion in human cognition is essential; emotions are not a luxury. Instead, emotions play a critical role in rational decision-making, in perception, in human interaction, and in human intelligence. These facts, combined with abilities computers are acquiring in expressing and recognizing affect, open new areas for research. This paper defines key issues in "affective computing," computing that relates to, arises from, or deliberately influences emotions. New models are suggested for computer recognition of human emotion, and both theoretical and practical applications are described for learning, human-computer interaction, perceptual information retrieval, creative arts and entertainment, human health, and machine intelligence. Significant potential advances in emotion and cognition theory hinge on the development of affective computing, especially in the form of wearable computers. This paper establishes challenges and future directions for this emerging field.

There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the "symbol grounding problem": How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their (arbitrary) shapes, be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: (1) "iconic representations" , which are analogs of the proximal sensory projections of distal objects and events, and (2) "categorical representations" , which are learned and innate feature-detectors that pick out the invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their (nonsymbolic) categorical representations. Higher-order (3) "symbolic representations" , grounded in these elementary symbols, consist of symbol strings describing category membership relations (e.g., "An X is a Y that is Z"). Connectionism is one natural candidate for the mechanism that learns the invariant features underlying categorical representations, thereby connecting names to the proximal projections of the distal objects they stand for. In this way connectionism can be seen as a complementary component in a hybrid nonsymbolic/symbolic model of the mind, rather than a rival to purely symbolic modeling. Such ...

alancing operation is not uniquely determined by the operation alone, since it depends on changes of state by deposit and withdraw operations that cannot be predicted or controlled. An object's operations return results that depend on changes of state controlled by unpredictable external actions. The growing pains of software technology are due to the fact that programming in the large is inherently interactive and cannot be expressed by or reduced to programming in the small. The behavior of airline reservation systems and other embedded systems cannot be expressed by algorithms. Fred Brooks's persuasive argument [1] that there is no silver bullet for specifying complex systems is a consequence of the irreducibility of interactive systems to algorithms. If silver bullets are interpreted as formal (or algorithmic) system specifications, the nonexistence of silver bullets can actually be proved. Artificial intelligence has undergone a paradigm shift from logic-based to interactive

this document, text or image about?' Gradually moving from the left to the right in Figure 3.1, different understandings of this concept evolve

This paper describes Soccer Server, a simulator of the game of soccer designed as a test-bench for evaluating multi-agent systems and cooperative algorithms. In real life, successful soccer teams require many qualities, such as basic ball control skills, the ability to carry out plans, and teamwork. We believe that simulating such behaviors is a significant challenge for Computer Science, Artificial Intelligence and Robotics technologies. It is to promote the development of such technologies, and to help define a new standard problem for research, that we have developed Soccer Server. We demonstrate the potential of Soccer Server by reporting an experiment that uses the system to compare the performance of a neural network architecture and a decision tree algorithm at learning the selection of soccer play-plans. Other researchers using Soccer Server to investigate the nature of cooperative behavior in a multi-agent environment will have the chance to assess their progress at RoboCup-97...

XIII SAMENVATTING XV ACKNOWLEDGEMENTS XVII 1. INTRODUCTION 1 1.1 The Aims 1 1.2 The Contributions 3 1.3 The Background 4 1.4 The Model 4 1.5 The Results 5 1.6 How to Read the Thesis 6 2. THE THEORETICAL BACKGROUND 9 2.1 Universal Tendencies of Human Sound Systems 9 2.1.1 Regularities of systems of speech sounds. 10 2.1.2 Regularities of speech sound sequences. 11 2.1.3 Explanations of regularities based on features. 11 2.1.4 Stevens' quantal theory of speech. 12 2.1.5 Carr' s distinctive region model. 12 2.1.6 Predicting sound systems as a whole. 13 2.1.7 How sound systems have become optimised. 14 2.1.8 Glotin' s AGORA model. 15 2.1.9 Berrah' s ESPECE model. 15 2.2 Steels' Work 16 2.2.1 Language as an open, complex dynamic system. 17 2.2.2 Language as an adaptive system. 18 2.2.3 Mechanisms of language origins. 18 2.2.4 Arguments against innateness of language. 20 2.3 The Use of Computer Simulations 21 iv 2.4 The Research Questions 22 3. THE SIMULATION 23 3.1 The History of the Simul...

The dynamical hypothesis is the claim that cognitive agents are dynamical systems. It stands opposed to the dominant computational hypothesis, the claim that cognitive agents are digital computers. This target article articulates the dynamical hypothesis and defends it as an open empirical alternative to the computational hypothesis. Carrying out these objectives requires extensive clarification of the conceptual terrain, with particular focus on the relation of dynamical systems to computers. Key words cognition, systems, dynamical systems, computers, computational systems, computability, modeling, time. Long Abstract The heart of the dominant computational approach in cognitive science is the hypothesis that cognitive agents are digital computers; the heart of the alternative dynamical approach is the hypothesis that cognitive agents are dynamical systems. This target article attempts to articulate the dynamical hypothesis and to defend it as an empirical alternative to the compu...

In AI, consciousness of self consists in a program having certain kinds of facts about its own mental processes and state of mind. We discuss what consciousness of its own mental structures a robot will need in order to operate in the common sense world and accomplish the tasks humans will give it. It's quite a lot. Many features of human consciousness will be wanted, some will not, and some abilities not possessed by humans have already been found feasible and useful in limited contexts. We give preliminary fragments of a logical language a robot can use to represent information about its own state of mind. A robot will often have to conclude that it cannot decide a question on the basis of the information in memory and therefore must seek information externally. Godel's idea of relative consistency is used to formalize non-knowledge. Programs with the kind of consciousness discussed in this article do not yet exist, although programs with some components of it exist. Thinking about c...

ion-Partitioned Evaluator (APE) architecture which has been tested in a simulated, single-agent, indoor navigation domain [SH90]. The APE architecture is composed of a number of concurrent, hierarchically abstract action control layers, each representing and reasoning about some particular aspect of the agent's task domain. Implemented as a parallel blackboard-based planner, the five layers --- sensor/motor, spatial, temporal, causal, and conventional (general knowledge) --- effectively partition the agent's data processing duties along a number of dimensions including temporal granularity, information/resource use, and functional abstraction. Perceptual information flows strictly from the agent sensors (connected to the sensor /motor level) toward the higher levels, while command or goal-achievement information flows strictly downward towards the agent's effectors (also connected to the sensor/motor level). Besides mechanisms for communicating with other layers, each layer in the AP...