Two analogy strategies: the cases of mind metaphors and introspection

Analogical reasoning is often employed in problem-solving and metaphor interpretation. This paper submits that, as a default, analogical reasoning addressing these different tasks employs different mapping strategies. In problem-solving, it employs analogy-maximising strategies (like structure mapping, Gentner, D., & Markman, A. B. (1997). Structure mapping in analogy and similarity. American Psychologist, 52, 45–56); in metaphor interpretation, analogy-minimising strategies (like ATT-Meta, Barnden, J. A. (2015). Open-ended elaborations in creative metaphor. In T. R. Besold, M. Schorlemmer, & A. Smaill (Eds.), Computational creativity research: Towards creative machines (pp. 217–242). Berlin: Springer). The two strategies interact in analogical reasoning with conceptual metaphors. This interaction leads to predictable fallacies. The paper supports these hypotheses through case-studies on “mind” metaphors from ordinary discourse, and abstract problem-solving in the philosophy of mind, respectively. It shows that (1) default metaphorical interpretations for vision- and space-cognition metaphors can be derived with a variant of the analogy-minimising ATT-Meta approach, (2) philosophically influential introspective conceptions of the mind can be derived with conceptual metaphors only through an analogy-maximising strategy, and (3) the interaction of these strategies leads to hitherto unrecognised fallacies in analogical reasoning with metaphors. This yields a debunking explanation of introspective conceptions.     

Transfer in Cognition

The purpose of this paper is to review the cognitive literature regarding transfer in order to provide a context for the consideration of transfer in neural networks. We consider transfer under the three general headings of analogy, skill transfer and metaphor. The emphasis of the research in each of these areas is quite different and the literatures are largely distinct. Important common themes emerge, however, relating to the role of similarity, the importance of 'surface content' and the nature of the representations that are used. We will draw out these common themes and note ways of facilitating transfer. We also briefly note possible implications for the study of transfer in neural networks.     

Learning Recursive Distributed Representations for Holistic Computation

A number of connectionist models capable of representing data with compositional structure have recently appeared. These new models suggest the intriguing possibility of performing holistic structure-sensitive computations with distributed representations. Two possible forms of holistic inference, transformational inference and confluent inference, are identified and compared. Transformational inference was successfully demonstrated by Chalmers; however, the pure transformational approach does not consider the eventual inference tasks during the process of learning its representations. Confluent inference is introduced as a method for achieving a tight coupling between the distributed representations of a problem and the solution for the given inference task while the net is still learning its representations. A dual-ported RAAM architecture based on Pollack's Recursive Auto-Associative Memory is implemented and demonstrated in the domain of Natural Language translation.     

Symbol Grounding or the Emergence of Symbols? Vocabulary Growth in Children and a Connectionist Net

The Symbolic Grounding Problem is viewed as a by-product of the classical cognitivist approach to studying the mind. In contrast, an epigenetic interpretation of connectionist approaches to studying the mind is shown to offer an account of symbolic skills as an emergent, developmental phenomenon. We describe a connectionist model of concept formation and vocabulary growth that auto-associates image representations and their associated labels. The image representations consist of clusters of random dot figures, generated by distorting prototypes. Any given label is associated with a cluster of random dot figures. The network model is tested on its ability to reproduce image representations given input labels alone (comprehension) and to identify labels given input images alone (production). The model implements several well-documented findings in the literature on early semantic development; the occurrence of over- and under-extension errors; a vocabulary spurt; a comprehension/production asymmetry; and a prototype effect. It is shown how these apparently disparate findings can be attributed to the operation of a single underlying mechanism rather than by invoking separate explanations for each phenomenon. The model represents a first step in the direction of providing a formal explanation of the emergence of symbolic behaviour in young children.     

Towards a computational- and algorithmic-level account of concept blending using analogies and amalgams

ABSTRACT

Concept blending – a cognitive process which allows for the combination of certain elements (and their relations) from originally distinct conceptual spaces into a new unified space combining these previously separate elements, and enables reasoning and inference over the combination – is taken as a key element of creative thought and combinatorial creativity. In this article, we summarise our work towards the development of a computational-level and algorithmic-level account of concept blending, combining approaches from computational analogy-making and case-based reasoning (CBR). We present the theoretical background, as well as an algorithmic proposal integrating higher-order anti-unification matching and generalisation from analogy with amalgams from CBR. The feasibility of the approach is then exemplified in two case studies.     

Syntactic Transformations on Distributed Representations

There has been much interest in the possibility of connectionist models whose representations can be endowed with compositional structure, and a variety of such models have been proposed. These models typically use distributed representations that arise from the functional composition of constituent parts. Functional composition and decomposition alone, however, yield only an implementation of classical symbolic theories. This paper explores the possibility of moving beyond implementation by exploiting holistic structure-sensitive operations on distributed representations. An experiment is performed using Pollack's Recursive Auto-Associative Memory (RAAM). RAAM is used to construct distributed representations of syntactically structured sentences. A feed-forward network is then trained to operate directly on these representations, modeling syntactic transformations of the represented sentences. Successful training and generalization is obtained, demonstrating that the implicit structure present in these representations can be used for a kind of structure-sensitive processing unique to the connectionist domain.     

Optimized inspection design for the thermographic characterization of sub-pixel sized through cracks

Non-destructive evaluation of structural components is critical for reducing costs from unnecessary replacements and maintenance. We study the utility of a non-contact modality for the inspection of thin metal plates for the presence of through cracks. Sensitivity to early stages of deterioration allows for simpler and less expensive repair than if a flaw propagates and becomes more damaging. Hence, we focus on the characterization of very small cracks with a thermal imaging technique. Through cracks interact with the flow of heat within a component, so that the characterization of cracks from a thermal image amounts to solving an inverse problem to discover unknown parameters that describe the crack.We consider cracks with length of less than a millimeter, falling under the pixel resolution of the recording thermal camera. Although these flaws are not directly visible from imaging data, the well-understood theory of heat conduction can be used in inference of crack properties. Herein we present a method to design an inspection modality that yields optimal data for such inference. Numerical experiments are performed to compare our optimized inspection setup to previous thermographic inspection scenarios found in the literature. Our design is found to produce the same quality of inference as these previous experiments which require much more expensive equipment (e.g. more powerful lasers and more sensitive IR cameras).     

The Connectionist Construction of Psychological Spaces

The application of connectionist learning procedures to the development of psychological internal representations requires a constraining theory of mental structure. The psychological space construct is advanced for this role and, consequently, a connectionist network which learns the multi-dimensionally scaled representations of a set of stimuli is developed. The model assumes that the function relating similarity to distance in psychological space is an exponential decay function, operates under the family of Minkowskian metrics and is able to determine the appropriate dimensionality of the psychological spaces it derives. The model is demonstrated on both separable and integral stimuli, and the validity of its application of gradient descent optimization principles over the city-block metric is examined. Several modelling extensions are discussed, including means by which the model might learn more general psychophysical mappings, and be able to derive internally the measures of psychological similarity currently provided through a similarity matrix.     

(S)RAAM: An Analytical Technique for Fast and Reliable Derivation of Connectionist Symbol Structure Representations

Recursive auto-associative memory (RAAM) has become established in the connectionist literature as a key contribution in the strive to develop connectionist representations of symbol structures. However, RAAMs use the backpropagation algorithm and therefore can be difficult to train and slow to learn. In addition, it is often hard to analyze exactly what a network has learnt and, therefore, it is difficult to state what composition mechanism is used by a RAAM for constructing representations. In this paper, we present an analytical version of RAAM, denoted as simplified RAAM or (S)RAAM. (S)RAAM models a RAAM very closely in that a single constructor matrix is derived which can be applied recursively to construct connectionist representations of symbol structures. The derivation, like RAAM, exhibits a moving target effect because training patterns adjust during learning but, unlike RAAM, the training is very fast. The analytical model allows a clear statement to be made about generalization characteristics and it can be shown that, in practice, the model will converge.     

Self-organized intermittent plastic flow in bulk metallic glasses

Under stress, bulk metallic glasses irreversibly deform through shear banding processes that manifest as serrated flow behavior. These serration events exhibit a shock-and-aftershock, earthquake-like behavior. Statistical analysis shows that the shear avalanches can self-organize to a critical state (SOC). In analogy to the smooth macroscopic-scale crystalline plasticity that arises from the spatio-temporal averages of disruptive earthquake-like events at the nanometer scale, shear avalanches in glassy metals are another model system that can be used to study SOC behavior. With our understanding of SOC behavior, we further demonstrate how to enhance the plasticity of glassy (brittle) materials. It is expected that the findings can be extended to other glassy or brittle materials.     

An electrical analog model of hydrogen trapping in iron alloys

A simple analogy has been developed to simulate bulk and surface trapping of hydrogen by titanium substitutional solute atoms in α-iron at room temperature. The analogy is based on the similarity between the ability of a capacitor to store electrons and of a trap to retain hydrogen. Simple formulae have been developed to analyze experimental data. Values are given for bulk and surface trap occupancy, as well as for the interaction energy TiH.     

Semantic systematicity and context in connectionist networks

A bstract . Fodor and Pylyshyn argued that connectionist models could not be used to exhibit and explain a phenomenon that they termed systematicity, and which they explained by possession of composition syntax and semantics for mental representations and structure sensitivity of mental processes. This inability of connectionist models, they argued, was particularly serious since it meant that these models could not be used as alternative models to classical symbolic models to explain cognition. In this paper, a connectionist model is used to identify some properties which collectively show that connectionist networks supply means for accomplishing a stronger version ofsystematicity than Fodor and Pylyshyn opted for. It is argued that 'context-dependent systematicity' is achievable within a connectionist framework. The arguments put forward rest on a particular formulation of content and context of connectionist representation, firmly and technically based on connectionist primitives in a learning environment. The perspective is motivated by the fundamental differences between the connectionist and classical architectures, in terms of prerequisites, lower-level functionality and inherent constraints. The claim is supported by a set of experiments using a connectionist architecture that demonstrates both an ability of enforcing, what Fodor and Pylyshyn term systematic and nonsystematic processing using a single mechanism, and how novel items can be handled without prior classification. The claim relies on extended learning feedback which enforces representational context dependence.     

Grundvorgänge der Korrosion von Metallen in organischen Lösungsmitteln II

Basic processes with the corrosion of metals in organic solvents (11) Research has been carried out into the corrosion mechanism of Zn, Fe and Ni in anhydrous primary alcohols of different chain lengths. The results can be explained from an analogy to aqueous solutions although the chain length of the plays an important part. With the corrosion of iron in the multi-components system heptane-ethanol-HCl(H₂SO₄)-O₂, a phase segregation can be observed which leads to processes similar to atmospheric corrosion. The destruction of the metal is due to a strongly acid solution phase deposited on the surface, governed by an electrolytic mechanism. The practice Of corrosion testing and corrosion Protection can be based on the Principles and methods conventionally used for corrosion in aqueous media.     

Constituent similarity and systematicity: The limits of first-order connectionism

Standard feedforward and recurrent networks cannot support strong systematicity when constituents are presented as local input/output vectors. To explain systematicity connectionists must either: (1) develop alternative models, or (2) justify the assumption of similar (non-local) constituent representations prior to the learning task. I show that the second commonly presumed option cannot account for systematicity, in general. This option, termed first-order connectionism, relies upon established spatial relationships between common-class constituents to account for systematic generalization: inferences (functions) learnt over, for example, cats, extend systematically to dogs by virtue of both being nouns with similar internal representations so that the function learnt to make inferences employing one simultaneously has the capacity to make inferences employing the other. But, humans generalize beyond common-class constituents. Cross-category generalization (e.g. inferences that require treating mango as a colour, rather than a fruit) makes having had the necessary common context to learn similar constituent representations highly unlikely. At best, the constituent similarity proposal encodes for one binary relationship between any two constituents, at any one time. It cannot account for inferences, such as transverse patterning, that require identifying and applying one of many possible binary constituent relationships that is contingent on a third constituent (i.e. ternary relationship). Connectionists are, therefore, left with the first option which amounts to developing models with the symbol-like capacity to represent explicitly constituent relations independent of constituent contents, such as in tensor-related models. However, rather just simply implementing symbol systems, I suggest reconciling connectionist and classical frameworks to overcome their individual limitations.     

The classification game: combining supervised learning and language evolution

We study the emergence of shared representations in a population of agents engaged in a supervised classification task, using a model called the classification game. We connect languages with tasks by treating the agents’ classification hypothesis space as an information channel. We show that by learning through the classification game, agents can implicitly perform complexity regularisation, which improves generalisation. Improved generalisation also means that the languages that emerge are well adapted to the given task. The improved language-task fit springs from the interplay of two opposing forces: the dynamics of collective learning impose a preference for simple representations, while the intricacy of the classification task imposes a pressure towards representations that are more complex. The push–pull of these two forces results in the emergence of a shared representation that is simple but not too simple. Our agents use artificial neural networks to solve the classification tasks they face, and a simple counting algorithm to learn a language as a form-meaning mapping. We present several experiments to demonstrate that both compositional and holistic languages can emerge in our system. We also demonstrate that the agents avoid overfitting on noisy data, and can learn some very difficult tasks through interaction, which they are unable to learn individually. Further, when the agents use simple recurrent networks to solve temporal classification tasks, we see the emergence of a rudimentary grammar, which does not have to be explicitly learned.     

Mechanical fault detection using fuzzy index fusion

This paper reports a simple, effective and robust fusion approach based on fuzzy logic and Sugeno-style inference engine. Using this method, four condition-monitoring indicators, developed for detection of transient and gradual abnormalities, are fused into one single comprehensive fuzzy fused index (FFI) for reliable machinery health assessment. This approach has been successfully tested and validated in two different applications: tool condition monitoring in milling operations and bearing condition assessment. The FFI differentiates clearly between the normal and abnormal conditions using the same fuzzy rule base. This certainly shows the versatility and robustness of the FFI. As the FFI value always falls between zero and one, it facilitates threshold setting in monitoring conditions of different tools or machinery components. Our experimental study also indicates that the FFI is sensitive to fault severity, capable of differentiating damages caused by an identical fault at different bearing components, but not susceptible to load changes.     

A methodology to forecast some attributes of an automatic storyteller’s outputs

ABSTRACT

This paper reports an extension of the program MEXICA, an automatic plot generator. The purpose of this project is to build a framework that permits studying the relations between MEXICA’s processes, its knowledge structures and the features of the produced narratives. We describe a methodology to analyse the features of the agent’s knowledge-base, to further establish correlations between such features and a set of general characteristics of the tales that they produce. Next, we make use of those correlations to forecast some properties of the future tales to be developed by different MEXICAs agents with different knowledge-bases. For this task, we introduce the S-graphs, representations of the similarity and organisation of the knowledge-structures. The results we obtained indicate that we are able to correctly forecast some of the features of tales to be produced; however, much more work is required.     

���������������������̵���̬ģ�������о�

 分析了薄板坯连铸连轧工艺流程的热态模拟要点，为薄板坯连铸连轧工艺流程的工艺优化和产品开发提供了合理的模拟方法。该方法与现场生产具有良好的相关性，具有精确控制钢水成分、轧制方案选择多样化等优点。     

High-level Inferencing in a Connectionist Network

Connectionist models have had problems representing and applying general knowledge rules that specifically require variables. This variable binding problem has barred them from performing the high-level inferencing necessary for planning, reasoning, and natural language understanding. This paper describes ROBIN, a structured neural network model capable of high-level inferencing requiring variable bindings and rule application. Variable bindings are handled by signatures—activation patterns which uniquely identify the concept bound to a role. Signatures allow multiple role-bindings to be propagated across the network in parallel for rule application and dynamic inference path instantiation. Signatures are integrated within a connectionist semantic network structure whose constraint-relaxation process selects between those newly-instantiated inferences. This allows ROBIN to handle an area of high-level inferencing difficult even for symbolic models, that of resolving multiple constraints from context to select the best interpretation from among several alternative and possibly ambiguous inference paths.