In human vision, the processes and the representations involved in identifying specific individuals are frequently assumed to be different from those used for basic-level classification, because classification is largely viewpoint-invariant, but identification is not. This assumption was tested in psychophysical experiments, in which objective similarity between stimuli (and, consequently, the level of their distinction) varied in a controlled fashion. Subjects were trained to discriminate between two classes of computer generated 3D objects, one resembling monkeys, and the other dogs. Both classes were defined by the same set of 56 parameters, which encoded sizes, shapes, and placement of the limbs, the ears, the snout, etc. Interpolation between parameter vectors of the class prototypes yielded shapes that changed smoothly between monkey and dog. Within-class variation was induced in each trial by randomly perturbing all the parameters. After the subjects reached 90% correct performa...

this paper is to present such a reformulation. The cell assembly provides the cognitive system with flexibility far beyond the simple activation of concepts. Instead of viewing the assembly as simply active or latent we see the activation of the assembly as coming in a series of phases. Each phase of activity serves a different purpose, giving the theory the power and flexibility to handle a wide range of psychological data.

We have used an automatic programming method called Genetic Programming (GP) for control of a miniature robot. Our earlier work on real-time learning suffered from the drawback of the learning time being limited by the response dynamics of the robot's environment. In order to overcome this problem we have devised a new technique which allows learning from past experiences that are stored in memory. The new method shows its advantage when perfect behavior emerges in experiments quickly and reliably. It is tested on two control tasks, obstacle avoiding and wall following behavior, both in simulation and on the real robot platform Khepera.

The haven all memes depend on reaching is the human mind, but a human mind is itself an artifact created when memes restructure a human brain in order to make it a better habitat for memes. The avenues for entry and departure are modified to suit local conditions, and strengthened by various artificial devices that enhance fidelity and prolixity of replication: native Chinese minds differ dramatically from native French minds, and literate minds differ from illiterate minds. What memes provide in return to the organisms in which they reside is an incalculable store of advantages—with some Trojan horses thrown in for good measure... –Daniel Dennett, Consciousness Explained 1 Duplication Fodder A beautiful child close to me, six and the apple of her father’s eye, believes that Thomas the Tank Engine really exists. She believes in Father Christmas, and when she grows up her ambition is to be a tooth fairy. She and her school-friends

The computer metaphor of cognitivism that has had such a strong influence on cognitive science over recent decades seems to be confronted (again) by a competitor: the brain metaphor put forward by connectionism (e.g. [McClelland and Rumelhart 1986] and [Sejnowski et al. 1988]). Connectionism assumes that mental phenomena can be explained in terms of the parallel activation and interaction of a large number of units (model neurons). These units are linked by connections (artificial synapses) which modulate the transmitted activity. Knowledge is represented in these connections between the units and learning takes place by adjusting their strength. An important, and much emphasized, aspect of connectionist models is their emergent behaviour. The massive parallel interaction of a large number of simple units can lead to qualitatively different and more interesting forms of behaviour. Successes of this connectionist approach range from models of human

A simple game provides a framework within which agents can spontaneously self-organize. In this paper, we present this game, and develop basic theory underlying a robust method for distributed coordination based on this game. This method makes use of finite state automata, one associated with each agent, which guide the agents. We give a new, general method of analysis of these systems, which previously had been studied only in limited cases. We also provide a physical example, which should hint at the type of problems resolvable using this method. 1 Introduction: The Gur Game In many of the problems in distributed systems, we wish a collection of agents to cooperate on a task which is most easily controlled centrally (that is, from "outside" the system). In other words, we desire a mechanism capable of producing cooperation in the agents, with only a simple command from outside. In this paper, we develop such a mechanism using finite state automata associated with each agent. These au...

The distributed system is becoming increasingly popular, and this produces the need for more sophisticated distributed control techniques. In this paper, we present a method for distributed control using simple finite state automata. Each of the distributed entities is "controlled" by its associated automaton, in the sense that the entity examines the state of the automaton to determine its behavior. The result of the collective behavior of all of the entities is fed back to the automata, which change their state as a result of this feedback. We give a new method of analysis which derives the steady state behavior of this system as a whole, by decomposing it into two parts: describing and solving an imbedded auxiliary Markov chain, and analyzing the behavior of the system within each of the states of this auxiliary chain. Key Words: distributed algorithms, finite state automata, Markov chain, queueing theory, state aggregation 1 Introduction With the advent of powerful workstations...

We perform co-analysis of a set of man-made 3D objects to allow the creation of novel instances derived from the set. We analyze the objects at the part level and treat the anisotropic part scales as a shape style. The co-analysis then allows style transfer to synthesize new objects. The key to co-analysis is part correspondence, where a major challenge is the handling of large style variations and diverse geometric content in the shape set. We propose style-content separation as a means to address this challenge. Specifically, we define a correspondence-free style signature for style clustering. We show that confining analysis to within a style cluster facilitates tasks such as co-segmentation, content classification, and deformation-driven part correspondence. With part correspondence between each pair of shapes in the set, style transfer can be easily performed. We demonstrate our analysis and synthesis results on several sets of man-made objects with style and content variations.

We study self-referential sentences of the type related to the Liar paradox. In particular, we consider the problem of assigning consistent fuzzy truth values to collections of self-referential sentences. We show that the problem can be reduced to the solution of a system of nonlinear equations. Furthermore, we prove that, under mild conditions, such a system always has a solution (i.e. a consistent truth value assignment) and that, for a particular implementation of logical “and”, “or” and “negation”, the “mid-point ” solution is always consistent. Next we turn to computational issues and present several truth-value assignment algorithms; we argue that these algorithms can be understood as generalized sequential reasoning. In an Appendix we present a large number of examples of self-referential collections (including the Liar and the Strengthened Liar), we formulate the corresponding truth value equations and solve them analytically and / or numerically.

In our innovation-driven world we tend to lay concepts that have lost their attractiveness to rest and rush to embrace the next giant leap. However, in most fields of creation, patterns of reawakening of old, extinct innovations can be found. It often looks as if new technological and social concepts have a life of their own, survival instincts and adaptive properties: They simply refuse to die. Should these phenomena be resolved on an ad hoc basis or are they grounded in the foundation of social behavior or evolutionary processes of technology? In conditions in which continuum equations would predict the extinction of a population, the presently offered microscopic representation proves that individuals self-organize in spatiotemporally localized adaptive patches that ensure their survival, resilience, and development as a collective. A similar treatment can explain why so many innovations are inevitably reborn. Accordingly, in assessing the value of social ideas, trends and even wants we ought to consider longer time frames following the decline of innovations, otherwise we might prematurely and erroneously discard successful promising concepts.