Wai K. Yeap

Towards a computational theory of cognitive maps

Abstract A computational theory of cognitive maps is developed which can explain some of the current findings about cognitive maps in the psychological literature and which provides a coherent framework for future development. The theory is tested with several computer implementations which demonstrate how the shape of the environment is computed and how ones conceptual representation of the environment is derived. We begin with the idea that the cognitive mapping process should be studied as two loosely coupled modules: The first module, known as the raw cognitive map, is computed from information made explicit in Marrs 2 1 2 -D sketch and not from high-level descriptions of what we perceive. The second module, known as the full cognitive map, takes the raw cognitive map as input and produces different “abstract representations” for solving high-level spatial tasks faced by the individual.

Computing a representation of the local environment

Yeap (1988) argued that an important basis for computing a cognitive map is the ability to compute and recognise local environments. Although he has demonstrated how such local environments could be used to construct a raw cognitive map, he failed to produce an adequate algorithm for computing them. In this paper, a detailed study of this problem is presented. We argue that although each local environment computed forms a natural basis for constructing a raw cognitive map, it is not computed primarily to do so. Instead, it is computed for ones immediate needs (such as hunting a prey or escaping from danger). This change in perspective argues for a very different cognitive mapping process, namely one that computes local environments as the individual moves through the environment but these representations are not necessarily used to construct a raw map. The individual does not do so until there is evidence that it is going to stay. Consequently this simplifies the algorithm for computing a local environment and a new algorithm is thus proposed. Some results of our implementation are shown.

The Utility of Global Representations in a Cognitive Map

In this paper we propose the use of small global memory for a viewers immediate surroundings to assist in recognising places that have been visited previously. We call this global memory a Memory for the Immediate Surroundings (MFIS). Our previous work [1, 2] on building a cognitive map has focused on computing a representation for the different local spaces the viewer visits. The different local spaces which are computed can be connected together in the way they are experienced to form a topological network which is one aspect of a cognitive map of the spatial environment. The problem with topological representations is that using them one cannot easily detect that one is reentering a previously visited part of the environment if it is approached from a different side to the one used previously. Thus we have developed a cognitive map representation which comprises an MFIS working in cooperation with the topological network. The idea that a global map is present as part of the cognitive mapping process is increasingly appealing. Robotics researchers have used them from the early days of autonomous mobile robots. However, they have shown that it is difficult to compute an accurate global representation because of errors. There is now increasing evidence that a global map is used in animals and many simulation models have incorporated the use of such a map. In this paper we review these works, discuss this notion of a global map in cognitive mapping, and show how one could be computed with minimum effort.

A kernel extreme learning machine algorithm based on improved particle swam optimization

Kernel extreme learning machine (KELM) increases the robustness of extreme learning machine (ELM) by turning linearly non-separable data in a low dimensional space into a linearly separable one. However, the internal power parameters of ELM are initialized at random, causing the algorithm to be unstable. In this paper, we use the active operators particle swam optimization algorithm (APSO) to obtain an optimal set of initial parameters for KELM, thus creating an optimal KELM classifier named as APSO-KELM. Experiments on standard genetic datasets show that APSO-KELM has higher classification accuracy when being compared to the existing ELM, KELM, and these algorithms combining PSO/APSO with ELM/KELM, such as PSO-KELM, APSO-ELM, PSO-ELM, etc. Moreover, APSO-KELM has good stability and convergence, and is shown to be a reliable and effective classification algorithm.

A Review of Component Coupling Metrics for Component-Based Development

The use of component-based software engineering (CBSE) is growing in popularity among the software engineering community and it has been successfully applied in many engineering domains. Component quality evaluations by adequate metrics are needed for large scale project. However, the software quality evaluation should also be performed on component assembly since the overall quality of the CBSE is more important. In this paper, we briefly survey the traditional software metrics and then discuss metrics for both the individual component and their assembly between the components. We then suggest a formal direct and an indirect component coupling metric.

A Split a Merge Approach to Metric-Topological Map-Building

We present a novel split and merge based method for dividing a given metric map into distinct regions, thus effectively creating a topological map on top of a metric one. The initial metric map is obtained from range data that are converted to a geometric map consisting of linear approximations of the indoor environment. The splitting is done using an objective function that computes the quality of a region, based on criteria such as the average region width (to distinguish big rooms from corridors) and overall direction (which accounts for sharp bends). A regularization term is used in order to avoid the formation of very small regions, which may originate from missing or unreliable sensor data. Experiments based on data acquired by a mobile robot equipped with sonar sensors are presented, which demonstrate the capabilities of the proposed method

Pronominal anaphora resolution using a shallow meaning representation of sentences

This paper describes a knowledge-poor anaphora resolution approach based on a shallow meaning representation of sentences. The structure afforded in such a representation provides immediate identification of local domains which are required for resolving pronominal anaphora. Other kinds of information used include syntactic information, structure parallelism and salience weights. We collected 111 singular 3rd person pronouns from open domain resources such as childrens novel and examples from several anaphora resolution papers. There are 111 third-person singular pronouns in the experiment data set and 94 of them demonstrate pronominal anaphora in domain of test data. The system successfully resolves 78.4% of anaphoric examples.

On the implementation of a theory of perceptual mapping

A recent theory of perceptual mapping argues that humans do not integrate successive views using a mathematical transformation approach to form a perceptual map. Rather, it is formed from integrating views at limiting points in the environment. Each view affords an adequate description of the spatial layout of a local environment and its limiting point is detected via a process of recognizing significant features in it and tracking them across views. This paper discusses the implementation of this theory on a laser-ranging mobile robot. Two algorithms were implemented to produce two different kinds of maps; one which is sparse and fragmented, and the other which is dense and detailed. Both algorithms successfully generated maps that preserve well the layout of the environment. The implementation provides insights into the problem of loop closing, moving in featureless environments, seeing a stable world, and augmenting mapping with commonsense knowledge.

Emperor AI, Where Is Your New Mind?

Any theory of the mind must explain how the mind works, and an AI theory is no exception. May critics have correctly argued that AI researchers have failed to produce such a theory. However, their discussion has focused mainly on what current computers (or particular programs) can or cannot do. Few have examined whether the field itself provides a foundation for producing a theory of the mind. If it does, what has been learned, and what do we need to do next? This article is an attempt to show how AI research has progressed in its quest for a theory of the mind.

How Albot0 Finds Its Way Home: A Novel Approach to Cognitive Mapping Using Robots

Much of what we know about cognitive mapping comes from observing how biological agents behave in their physical environments, and several of these ideas were implemented on robots, imitating such a process. In this paper a novel approach to cognitive mapping is presented whereby robots are treated as a species of their own and their cognitive mapping is being investigated. Such robots are referred to as Albots. The design of the first Albot, Albot0 , is presented. Albot0 computes an imprecise map and employs a novel method to find its way home. Both the map and the return-home algorithm exhibited characteristics commonly found in biological agents. What we have learned from Albot0 s cognitive mapping are discussed. One major lesson is that the spatiality in a cognitive map affords us rich and useful information and this argues against recent suggestions that the notion of a cognitive map is not a useful one.