Describes robust neurocontrollers for groups of agents that perform construction tasks. They enable agents to balance multiple goals, perform sequences of actions and survive while building walls, corridors, intersections, and briar patches.

The tasks that animals perform require a high degree of intelligence. Animals forage for food, migrate, navigate, court mates, rear offspring, defend against predators, construct nests, and so on. These tasks commonly require social interaction/cooperation and are accomplished by animal nervous systems, which are the result of billions of years of evolution and complex developmental/learning processes. The Artificial Life (AL) approach to synthesizing intelligent behavior is guided by this biological perspective. In this article we examine some of the numerous open problems in synthesizing intelligent animal behavior (especially cooperative behavior involving communication) that face the field of AL, a discipline still in its infancy.

Abstract

In Part 1 of this two-part series, we introduced Katamic memory—a neural network architecture capable of robust sequence learning and recognition. In Part 2, we introduce the Blobs World taskjdomain for language learning and describe the DETE language learning system, which is composed of over 50 Katamic memory modules. DETE currently learns small subsets of English and Spanish via association with perceptual! motor inputs. In addition to Kaiamic memory, DETE employs several other novel features: (1) use of feature planes, to encode visual shapes, spatial relationships and the motions of objects, (2) phase-locking of neural firing, in order to represent focus of atention and to bind objects across multiple feature planes, and (3) a method for encoding temporal relationships, so that DETE can learn utterances involving the immediate past and future. We compare DETE to related models and discuss the implications of this approach for language-learning research.

Distributed connectionist (DC) systems offer a set of processing features which are distinct from those provided by traditional symbol processing (SP) systems. In general, the features of DC systems are derived from the nature of their distributed representations. Such representations have a microsemantics -i.e. symbols with similar internal representations tend to have similar processing effects. In contrast, the symbols in SP systems have no intrinsic microsemantics of their own; e.g. SP symbols are formed by concatenating ASCII codes that are static, human engineered and arbitrary. Such symbols possess only a macrosemantics - i.e. symbols are placed into structured relationships with other symbols, via pointers, and bindings are propagated via variables. The fact that DC and SP systems each provide a distinct set of useful features serves as a strong research motivation for seeking a synthesis. What is needed for such a synthesis is a method by which symbols can dynamically form their own microsemantics, while at the same time entering into structured, recursive relationships with other symbols, thus developing also a macrosemantics. Here, we describe a general method, called symbol recirculation, for allowing symbols to form their own microsemantics. We then discuss three techniques for implementing variables and bindings in DC systems. Finally, we describe a number of DC systems, based on these techniques, which perform a variety of high-level cognitive tasks.

Searle (1980, 1989) has produced a number of arguments purporting to show that computer programs, no matter how intelligently they may act, lack ‘ intentionality’ Recently, Harnad (1989) has accepted Searle' s arguments as having ‘ shaken the foundations of Artificial Intelligence’ (p. 5). To deal with Searle' s arguments, Harnad has introduced the need for ‘ noncomputational devices’ (e.g. transducers) to realize ‘ symbol grounding’ This paper critically examines both Searle' s and Hamad' s arguments and concludes that the foundations of AT remain unchanged by these arguments, that the Turing Test remains adequate as a test of intentionality, and that the philosophical position of computationalism remains perfectly reasonable as a working hypothesis for the task of describing and embodying intentionality in brains and machines.

In the law, decisions in previous cases play a significant role in the presentation, understanding, and outcome of new cases. This is particularly true in the area of contract law where few statutes (explicit legal rules) exist. When presented with a new case, a lawyer must be able to identify important issues and make some predictions about how the case might be decided. The lawyer will often recall past cases which bear similarities to the current case and reason analogically to make these predictions. In order to perform these tasks, a lawyer must be able to remember past cases, organize them in memory so that cases that are conceptually similar are stored together (a lawyer normally won't be reminded of an irrelevant case), and make analogies between cases. Thus the organization and representation of knowledge in memory is crucial in building a model of lawyer's cognitive processes. This paper describes a process model, implemented in a computer program called STARE, which addresses these issues in the context of first-year law students learning contract law.

Here we address the problem of mapping phrase meanings into their conceptual representations. Figurative phrases are pervasive in human communication, yet they are difficult to explain theoretically. In fact, the ability to handle idiosyncratic behavior of phrases should be a criterion for any theory of lexical representation. Due to the huge number of such phrases in the English language, phrase representation must be amenable to parsing, generation, and also to learning. In this paper we demonstrate a semantic representation which facilitates, for a wide variety of phrases, both learning and parsing.

A description is given of a procedure for certifying the reliability of software before its release to users. The ingredients of this procedure are a life cycle of executable product increments, representative statistical testing, and a standard estimate of the MTTF (mean time to failure) of the product at the time of its release. The authors also discuss the development of certified software products and the derivation of a statistical model used for reliability projection. Available software test data are used to demonstrate the application of the model in certification process.

The problem of manually modifying the lexicon appears with any natural language processing program.Ideally, a program should be able to acquire new lexieal entries from context, the way people learn.We address the problem of acquiring entire phrases, specifically Jigurative phr~es, through augmenting a phr~al lezico~ Facilitating such a self-extending lexicon involves (a) disambiguation~se|ection of the intended phrase from a set of matching phrases, (b) robust parsin~-comprehension of partially-matching phrases, and (c) error analysis---use of errors in forming hypotheses about new phrases.We have designed and implemented a program called RINA which uses demons to implement funetional-~rammar principles.RINA receives new figurative phrases in context and through the application of a sequence of failure-driven rules, creates and refines both the patterns and the concepts which hold syntactic and semantic information about phrases.