Active symbols and internal models: Towards a cognitive connectionism

In the first section of the article, we examine some recent criticisms of the connectionist enterprise: first, that connectionist models are fundamentally behaviorist in nature (and, therefore, non-cognitive), and second that connectionist models are fundamentally associationist in nature (and, therefore, cognitively weak). We argue that, for a limited class of connectionist models (feed-forward, pattern-associator models), the first criticism is unavoidable. With respect to the second criticism, we propose that connectionist modelsare fundamentally associationist but that this is appropriate for building models of human cognition. However, we do accept the point that there are cognitive capacities for which any purely associative model cannot provide a satisfactory account. The implication that we draw from is this is not that associationist models and mechanisms should be scrapped, but rather that they should be enhanced.In the next section of the article, we identify a set of connectionist approaches which are characterized by active symbols — recurrent circuits which are the basis of knowledge representation. We claim that such approaches avoid criticisms of behaviorism and are, in principle, capable of supporting full cognition. In the final section of the article, we speculate at some length about what we believe would be the characteristics of a fully realized active symbol system. This includes both potential problems and possible solutions (for example, mechanisms needed to control activity in a complex recurrent network) as well as the promise of such systems (in particular, the emergence of knowledge structures which would constitute genuine internal models).     

Translating VHDL into functional symbolic finite-state models

In this paper we present a method to translate VHDL into symbolic finite-state models. Our method can handle those aspects of VHDL which have a finite representation obtaining the semantics defined in the IEEE statndard. We describe an intermediate representation based on finite automata and its translation into a BDD-based reperesentation. Our model interfaces VHDL with a BDD-based functional symbolic model checker.The work of these authors is supported by ESPRIT project 6128 FORMAT.The work of this author is supported by the Volkswagenstiftung project Informatiksysteme.     

Supporting dispatchability in schedules with consumable resources

Earlier work on scheduling by autonomous systems has demonstrated that schedules in the form of simple temporal networks, with intervals of values for possible event-times, can be made dispatchable, i.e. executable incrementally in real time with guarantees against failure due to unfortunate event-time selections. In this work we show how the property of dispatchability can be extended to networks that include constraints for consumable resources. We first determine conditions for insuring that resource use does not exceed capacity under dispatchable execution for a single sequence of activities, or bout, involving one resource. Then we show how to handle interactions between resource and temporal constraints to insure dispatchability, how to enhance flexibility of resource use under these conditions, and how to handle multiple bouts interspersed with instances of resource release. Finally, we consider methods for establishing the necessary dispatchability conditions during schedule creation (planning stage). The results demonstrate that flexible handling of resource use can be safely extended to the execution layer to provide more effective deployment of consumable resources.     

An Undecidable Problem for Timed Automata

The reachability problem for timed automata is decidable when the coefficients in the guards are rational numbers. We show that the reachability problem is undecidable when the coefficients are chosen from the set . A consequence of this is that the parameter synthesis problem for timed automata with even a single parameter is undecidable. We discuss why such undecidability results arise in timed and hybrid systems, what they mean, and if it is possible to get around them.     

Situated action,symbol systems and universal computation

Vera & Simon (1993a) have argued that the theories and methods known as situated action or situativity theory are compatible with the assumptions and methodology of the physical symbol systems hypothesis and do not require a new approach to the study of cognition. When the central criterion of computational universality is added to the loose definition of a symbol system which Vera and Simon provide, it becomes apparent that there are important incompatibilities between the two approaches such that situativity theory cannot be subsumed within the symbol systems approach. Symbol systems and situativity theoretic approaches are, and should be seen to be, competing approaches to the study of cognition.     

Connectionism and Novel Combinations of Skills: Implications for Cognitive Architecture

In the late 1980s, there were many who heralded the emergence of connectionism as a new paradigm – one which would eventually displace the classically symbolic methods then dominant in AI and Cognitive Science. At present, there remain influential connectionists who continue to defend connectionism as a more realistic paradigm for modeling cognition, at all levels of abstraction, than the classical methods of AI. Not infrequently, one encounters arguments along these lines: given what we know about neurophysiology, it is just not plausible to suppose that our brains are digital computers. Thus, they could not support a classical architecture. I argue here for a middle ground between connectionism and classicism. I assume, for argument's sake, that some form(s) of connectionism can provide reasonably approximate models – at least for lower-level cognitive processes. Given this assumption, I argue on theoretical and empirical grounds that most human mental skills must reside in separate connectionist modules or sub-networks. Ultimately, it is argued that the basic tenets of connectionism, in conjunction with the fact that humans often employ novel combinations of skill modules in rule following and problem solving, lead to the plausible conclusion that, in certain domains, high level cognition requires some form of classical architecture. During the course of argument, it emerges that only an architecture with classical structure could support the novel patterns of information flow and interaction that would exist among the relevant set of modules. Such a classical architecture might very well reside in the abstract levels of a hybrid system whose lower-level modules are purely connectionist.     

The Discrete Event Concept as a Paradigm for the “Perception-Based Diagnosis” of Sachem

Sachem is an extensive large-scale real time knowledge-based system designed to monitor and diagnose blast furnaces. This paper aims at illustrating the way the concept of discrete event allowed the definition of a perception-based diagnosis approach as a recursive and holographic abstraction process of a discrete event. The example of the diagnosis of a thermal load phenomenon on a blast furnace is used in order to illustrate the way Sachem apply the perception-based diagnosis approach. Some considerations about the blast furnace and the development of Sachem are also presented in the paper to recall the complexity and the issue of the design of powerful perception systems.     

Soft computing in engineering design: a hybrid dual cross-mapping neural network model

Contemporary design process requires the development of a new computational intelligence or soft computing methodology that involves intelligence integration and hybrid intelligent systems for design, analysis and evaluation, and optimization. This paper first presents a discussion of the need to incorporate intelligence into an automated design process and the various constraints that designers face when embarking on industrial design projects. Then, it presents the design problem as optimizing the design output against constraints and the use of soft computing and hybrid intelligent systems techniques. In this paper, a soft-computing-integrated intelligent design framework is developed. A hybrid dual cross-mapping neural network (HDCMNN) model is proposed using the hybrid soft computing technique based on cross-mapping between a back-propagation network (BPNN) and a recurrent Hopfield network (HNN) for supporting modeling, analysis and evaluation, and optimization tasks in the design process. The two networks perform different but complementary tasks—the BPNN decides if the design problem is a type 0 (rational) or type 1 (non-rational) problem, and the output layer weights are then used as the energy function for the HNN. The BPNN is used for representing design patterns, training classification boundaries, and outputting network weight values to the HNN, and then the HNN uses the calculated network weight values to evaluate and modify or re-design the design patterns. The developed system provides a unified soft-computing-integrated intelligent design framework with both symbolic and computational intelligence. The system has self-modifying and self-learning functions. Within the system, only one network training is needed for accomplishing the evaluation, rectification/modification, and optimization tasks in the design process. Finally, two case studies are provided to illustrate and validate the developed model and system.     

SYMCON—A Hybrid Symbolic/Connectionist System for Word Sense Disambiguation

Connectionist methods and knowledge-based techniques are two largely complementary approaches to natural language processing (NLP). However, they both have some potential problems which preclude their being a general purpose processing method. Research reveals that a hybrid processing approach that combines connectionist with symbolic techniques may be able to use the strengths of one processing paradigm to address the weakness of the other one. Hence, a system that effectively combines the two different approaches can be superior to either one in isolation. This paper describes a hybrid system—SYMCON (SYMbolic and CONnectionist) which integrates symbolic and connectionist techniques in an attempt to solve the problem of word sense disambiguation (WSD), which is arguably one of the most fundamental and difficult issues in NLP. It consists of three sub-systems: first, a distributed simple recurrent network (SRN) is trained by using the standard back-propagation algorithm to learn the semantic relationships among concepts, thereby generating categorical constraints that are supplied to the other two sub-systems as the initial results of pre-processing. The second sub-system of SYMCON is a knowledge-based symbolic component consisting of a knowledge base containing general inferencing rules in a certain application domain. Third, a localist network is used to select the best interpretation among multiple alternatives and potentially ambiguous inference paths by spreading activation throughout the network. The structure, initial states, and connection weights of the network are determined by the processing outcome in the other two sub-systems. This localist network can be viewed as a medium between the distributed network and the symbolic sub-system. Such a hybrid symbolic/connectionist system combines information from all three sources to select the most plausible interpretation for ambiguous words.     

CesiumSpray: a Precise and Accurate Global Time Service for Large-scale Systems

In large-scale systems, such as Internet-based distributed systems, classical clock-synchronization solutions become impractical or poorly performing, due to the number of nodes and/or the distance among them. We present a global time service for world-wide systems, based on an innovative clock synchronization scheme, named CesiumSpray. The service exhibits high precision and accuracy; it is virtually indefinitely scalable; and it is fault-tolerant. It is deterministic for real-time machinery in the local area, which makes it particularly well-suited for, though not limited to, large-scale real-time systems. The main features of our clock synchronization scheme can be summarized as follows: hybrid external/internal synchronization protocol improves effectiveness of synchronization; heterogeneous failure semantics for clocks and processors improves previous lower bounds on processors; two-level hierarchy improves scalability. The root of the hierarchy is the GPS satellite constellation, which sprays its reference time over a set of nodes provided with GPS receivers, one per local network. The second level of the hierarchy performs internal synchronization, further spraying the external time inside the local network.     

An operation-control scheme for authorization in computer systems

The access-control authorization scheme, which is being used for the protection of operating systems, is found to be inadequate in other areas, such as in databases and information systems. A new authorization scheme, which is a natural extension of access control, is proposed. The new scheme, which is called operation control, is shown to be superior to the accesscontrol scheme in a number of ways. In particular, it facilitates more natural and efficient representations of policies, particularly the type of complex policies that appear in information systems, it facilitates enforcement by compile-time validation due to a greater stability of authority states, and it reduces the need for revocation.This work was partially supported by Grant DAHCIS-73-G6 of the Advanced Research Project Agency of the US government. This paper is a modified version of the paper An Activator-based protection scheme, July 1976 (SOSAP-TR-25).     

A socio-technical systems approach to studying interruptions: Understanding the interrupter's perspective

The purpose of this study was to understand the cognitive processes underlying nurses' decision to interrupt other nurses. The Institute of Medicine (2000) reported that interruptions are likely contributors to medical errors. Unfortunately, the research to date has been quite homogenous, focusing only on the healthcare provider being interrupted, ignoring the true complexities of interruptions. This study took a socio-technical approach being the first to examine interruptions from the viewpoint of the interrupting nurse. Over 15 h of observations and 10 open-ended interviews with expert nurses in a Neuroscience Surgical Intensive Care Unit were conducted. It was found that nurses conduct a quick cost-benefit assessment to determine the interruptibility of other nurses and whether an interruption is value-added vs. non-value added. To complete the assessment, nurses consider several conditional factors related to the interruptee, the interrupter, and the nature of the interruption content, and different potential consequences of the interruption.     

Constraint-Based Verification of Parameterized Cache Coherence Protocols

We propose a new method for the parameterized verification of formal specifications of cache coherence protocols. The goal of parameterized verification is to establish system properties for an arbitrary number of caches. In order to achieve this purpose we define abstractions that allow us to reduce the original parameterized verification problem to a control state reachability problem for a system with integer data variables. Specifically, the methodology we propose consists of the following steps. We first define an abstraction in which we only keep track of the number of caches in a given state during the execution of a protocol. Then, we use linear arithmetic constraints to symbolically represent infinite sets of global states of the resulting abstract protocol. For reasons of efficiency, we relax the constraint operations by interpreting constraints over real numbers. Finally, we check parameterized safety properties of abstract protocols using symbolic backward reachability, a strategy that allows us to obtain sufficient conditions for termination for an interesting class of protocols. The latter problem can be solved by using the infinite-state model checker HyTech: Henzinger, Ho, and Wong-Toi, A model checker for hybrid systems, Proc. of the 9th International Conference on Computer Aided Verification (CAV'97), Lecture Notes in Computer Science, Springer, Haifa, Israel, 1997, Vol. 1254, pp. 460–463. HyTech handles linear arithmetic constraints using the polyhedra library of Halbwachs and Proy, Verification of real-time systems using linear relation analysis, Formal Methods in System Design, Vol. 11, No. 2, pp. 157–185, 1997. By using this methodology, we have automatically validated parameterized versions of widely implemented write-invalidate and write-update cache coherence protocols like Synapse, MESI, MOESI, Berkeley, Illinois, Firefly and Dragon (Handy, The Cache Memory Book, Academic Press, 1993). With this application, we have shown that symbolic model checking tools like HyTech, originally designed for the verification of hybrid systems, can be applied successfully to new classes of infinite-state systems of practical interest.     

Redesign of a Systems Engineering Language: Formalisation of χ

This paper describes the redesign of a systems engineering language called . This is an engineering language designed to specify and analyse industrial systems. The main objective of this redesign was to enable mathematical reasoning about specifications. We discuss the original language, the requirements and design decisions, and the resulting syntax and semantics of the new version of , called . In particular, we elaborate on semantical aspects of s time model.     

Symbolic and Neural Learning Algorithms: An Experimental Comparison

Despite the fact that many symbolic and neural network (connectionist) learning algorithms address the same problem of learning from classified examples, very little is known regarding their comparative strengths and weaknesses. Experiments comparing the ID3 symbolic learning algorithm with the perception and backpropagation neural learning algorithms have been performed using five large, real-world data sets. Overall, backpropagation performs slightly better than the other two algorithms in terms of classification accuracy on new examples, but takes much longer to train. Experimental results suggest that backpropagation can work significantly better on data sets containing numerical data. Also analyzed empirically are the effects of (1) the amount of training data, (2) imperfect training examples, and (3) the encoding of the desired outputs. Backpropagation occasionally outperforms the other two systems when given relatively small amounts of training data. It is slightly more accurate than ID3 when examples are noisy or incompletely specified. Finally, backpropagation more effectively utilizes a distributed output encoding.     

A discrete event framework for autonomous observation under uncertainty

In this work we establish a framework for the general problem of observation, which may be applied to different kinds of visual tasks. We construct intelligent high-level control mechanisms for active visual recognition of different processes within a hybrid dynamic system. We address the problem of observing a manipulation process in order to illustrate the ideas and motive behind our framework. We use a discrete event dynamic system as a high-level structuring technique to model the manipulation system. The formulation utilizes the knowledge about the system and the different actions in order to solve the observer problem in an efficient, stable and practical manner. The model uses different tracking mechanisms so that the observer can see the workspace of the manipulating robot. An automaton is developed for the hand/object interaction over time and a stabilizing observer is constructed. Low-level modules are developed for recognizing the visual events that causes state transitions within the dynamic manipulation system in real time. A coarse quantization of the manipulation actions is used in order to attain an active, adaptive and goaldirected sensing mechanism. The formulation provides high-level symbolic interpretations of the scene under observation. The discrete event framework is augmented with mechanisms for recovering the continuous parametric evolution of the scene under observation and for asserting the state of the manipulation agent. This work examines closely the possibilities for errors, mistakes and uncertainties in the manipulation system, observer construction process and event identification mechanisms. We identify and suggest techniques for modeling these uncertainties. Ambiguities are allowed to develop and are resolved after finite time. Error recovery mechanisms are also devised. The computed uncertainties are utilized for navigating the observer automaton state space, asserting state transitions and developing a suitable tracking mechanism.     

The surface of language and humanities computing

Recent articles have noted that humanities computing techniques and methodologies remain marginal to mainstream literary scholarship. Mark Olsen's paper discusses this phenomenon and argues for large scale analyses of text databases that would incorporate a shift in theoretical orientation to include greater stress on intertextuality and sign theory. Part of Olsen's argument revolves on the need to move away from the syntactic and overt grammatical elements of textual language to more subtle semantics and meaning systems. While provocative and important, Olsen's stance remains rooted in literary theoretical constructs. Another level of language, the cognitive, offers equally interesting challenges for humanities computing, though the paradigms for this type of computer-based exploration are derived from disciplines traditionally removed from the humanities. The riddle, a nearly universal genre, offers a window onto some of the cognitive processes involved in deep level language function. By analyzing the riddling process, different methods of computational modelling can be inferred, suggesting new avenues for computing in the humanities.Charles Henry has a Ph.D. in Comparative Literature and is presently the Director of Libraries at Vassar College. His research includes non-literal aspects of language, and the cognitive processes involved in understanding symbolic language. Recent articles include The Image of Word,in Humanities and the Computer: New Directions, ed. D. Miall (Oxford, 1990), and Non-Literal Aspects of Language and Knowledge Structuring, inCybernetics and Systems Research '92, ed. R. Trappl (World Scientific Press, 1992).     

A cognitivist model for decision support: COGITA project, a problem formulation assistant

The formulation of a problem may be defined as a process of acquisition and organization of knowledge related to a given situation, on which a decision maker projects some action. The assistance in the problem formulation that we may expect within decision support systems is difficult to design and to implement. This is mainly due to the frequent lack of attention to a sufficiently formalized conceptual framework which would consider the decision with a more cognition sciences oriented approach. In the first part, we will present an instrumental model for the study of decision processes as an attempt to simulate the cognitive process of knowledge acquisition and organization carried out by a decision maker facing a problematic situation. Considering its epistemological foundations, this model can be named “cognitivist model”. Within this model, the decision is defined as a cognitive construction which we call “decisional construct”. It consists of the elaboration of one or several abstract representations of the problematic situation (formulation phase), and the design of operational models (solving phase). In the second part, we will present the COGITA project, which consists of the design and realization of an environment for the development of problem formulation assistance systems. The modelization and simulation of cognitive processes call for relevant techniques originating either in artificial intelligence or in connectionism. We will show which are the main characteristics, potentials, limits and complementarity of these techniques and why their integration is fundamental and necessary to the simulation of the cognitive process associated with the formulation. COGITA is a hybrid system currently under development which tends to integrate symbolic artificial intelligence techniques and connectionist models in a cooperative hybridation the general architecture of which is presented.     

Stability radii of infinite-dimensional positive systems

We show that for infinite-dimensional discrete-time positive systems the complex and real stability radii coincide. Furthermore, we provide a simple formula for the complex stability radius of positive systems by the associated transfer function. We illustrate our results with an example dealing with a simple type of differential-difference equations.The author would like to thank the Deutsche Forschungsgemeinschaft for its support during this work.