Linking Symbolic and Subsymbolic Computing

The growing interest in integrating symbolic and subsymbolic computing techniques is manifested by the increasing number of hybrid systems that employ both methods of processing. In this paper, a general-purpose mechanism for linking symbolic and subsymbolic computing is introduced. Through the use of programming abstractions, an intermediary agent called a supervisor is created and bound to each subsymbolic network. The role of a supervisor is to monitor and control the network behavior and interpret its output. Details of the subsymbolic computation are hidden behind a higher level interface, enabling symbolic and sybsymbolic components to interact at corresponding conceptual levels. Module level parallelism is achieved because subsymbolic modules execute independently. Methods for construction of hierarchical systems of subsymbolic modules are also provided.     

A corpus-based connectionist architecture for large-scale natural language parsing

We describe a deterministic shift-reduce parsing model that combines the advantages of connectionism with those of traditional symbolic models for parsing realistic sub-domains of natural language. It is a modular system that learns to annotate natural language texts with syntactic structure. The parser acquires its linguistic knowledge directly from pre-parsed sentence examples extracted from an annotated corpus. The connectionist modules enable the automatic learning of linguistic constraints and provide a distributed representation of linguistic information that exhibits tolerance to grammatical variation. The inputs and outputs of the connectionist modules represent symbolic information which can be easily manipulated and interpreted and provide the basis for organizing the parse. Performance is evaluated using labelled precision and recall. (For a test set of 4128 words, precision and recall of 75% and 69%, respectively, were achieved.) The work presented represents a significant step towards demonstrating that broad coverage parsing of natural language can be achieved with simple hybrid connectionist architectures which approximate shift-reduce parsing behaviours. Crucially, the model is adaptable to the grammatical framework of the training corpus used and so is not predisposed to a particular grammatical formalism.     

Connectionist Finite State Natural Language Processing

Unless one is prepared to argue that existing, ‘classical’formal language and automata theory, together with the natural language linguistics built on them, are fundamentally mistaken about the nature of language, any viable connectionist natural language processing (NLP) model will have to be characterizable, at least approximately, by some generative grammar or by an automaton of the corresponding class. An obvious way of ensuring that a connectionist NLP device is so characterizable is to specify it in classical terms and then to implement it in an artificial neural network, and that is what this paper does. It adopts the deterministic pushdown transducer (DPDT) as an adequate formal model for general NLP and shows how a simple recurrent network (SRN) can be trained to implement a finite state transducer (FST) which simulates the DPDT. A computer simulation of a parser for a small fragment of English is used to study the properties of the model. The conclusion is that such SRN implementation results in a device which is broadly consistent with its classical specification, but also has emergent properties relative to that specification which are desirable in an NLP device.     

A Hybrid Symbolic/Connectionist Model for Noun Phrase Understanding

This paper describes a hybrid model which integrates symbolic and connectionist techniques for the analysis of noun phrases. Our model consists of three levels: (1) a distributed connectionist level, (2) a localist connectionist level, and (3) a symbolic level. While most current systems in natural language processing use techniques from only one of these three levels, our model takes advantage of the virtues of all three processing paradigms. The distributed connectionist level provides a learned semantic memory model. The localist connectionist level integrates semantic and syntactic constraints. The symbolic level is responsible for restricted syntactic analysis and concept extraction. We conclude that a hybrid model is potentially stronger than models that rely on only one processing paradigm.     

Integrating Neural and Symbolic Approaches: A Symbolic Learning Scheme for a Connectionist Associative Memory

This paper deals with the integration of neural and symbolic approaches. It focuses on associative memories where a connectionist architecture tries to provide a storage and retrieval component for the symbolic level. In this light, the classic model for associative memory, the Hopfield network is briefly reviewed. Then, a new model for associative memory, the hybrid Hopfield-clique network is presented in detail. Its application to a typically symbolic task, the post -processing of the output of an optical character recognizer, is also described. In the author's view, the hybrid Hopfield -clique network constitutes an example of a successful integration of the two approaches. It uses a symbolic learning scheme to train a connectionist network, and through this integration, it can provide perfect storage and recall. As a conclusion, an analysis of what can be learned from this specific architecture is attempted. In the case of this model, a guarantee for perfect storage and recall can only be given because it was possible to analyze the problem using the well-defined symbolic formalism of graph theory. In general, we think that finding an adequate formalism for a given problem is an important step towards solving it.     

Cognition and the computational power of connectionist networks

This paper examines certain claims of 'cognitive significance' which (wisely or not) have been based upon the theoretical powers of three distinct classes of connectionist networks, namely, the 'universal function approximators', recurrent finite-state simulation networks and Turing equivalent networks. Each class will be considered with respect to its potential in the realm of cognitive modelling. Regarding the first class, I argue that, contrary to the claims of some influential connectionists, feed-forward networks do not possess the theoretical capacity to approximate all functions of interest to cognitive scientists. For example, they cannot approximate many important, recursive (halting) functions which map symbolic strings onto other symbolic strings. By contrast, I argue that a certain class of recurrent networks (i.e. those which closely approximate deterministic finite automata (DFA)) shows considerably greater promise in some domains. However, from a cognitive standpoint, difficulties arise when we consider how the relevant recurrent networks could acquire the weight vectors needed to support DFA simulations. These difficulties are severe in the realm of central high-level cognitive functions. In addition, the class of Turing equivalent networks is here examined. It is argued that the relevance ofsuch networks to cognitive modelling is seriously undermined by their reliance on infinite precision in crucial weights and/or node activations. I also examine what advantages these networks might conceivably possess over and above classical symbolic algorithms. For, from a cognitive standpoint, the Turing equivalent networks present difficulties very similar to certain classical algorithms; they appear highly contrived, their structure is fragile and they exhibit little or no noise tolerance.     

Ultra-precision machining by the hydrodynamic polishing process

This study will examine the feasibility of applying the hydrodynamic polishing (HDP) process as an ultra-precision machining method, which is aimed to compensate the form error of a work surface so that the form precision is improved. To be an ultra-precision machining method, the HDP process is required to have a deterministic machining nature and to have the capability to machine an arbitrary shape. From the machining mechanism, four sets of parameters that dominate the deterministic properties of the process are identified. It is clearly demonstrated from the experimental study that the HDP process is deterministic if the identified parameters are well controlled. To machine an arbitrary shape, a machining principle is proposed. From this principle, a square slot with uniform depth and a semi-cylindrical profile with parabolic cross-section can be accurately obtained by the HDP process. Hence, the HDP process can be a promising method to compensate form error for the ultra-precision purpose.     

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.     

The cultural evolution of communication in a population of neural networks

Human language is learned, symbolic and exhibits syntactic structure, a set of properties which make it unique among naturally-occurring communication systems. How did human language come to be as it is? Language is culturally transmitted and cultural processes may have played a role in shaping language. However, it has been suggested that the cultural transmission oflanguage is constrained by some language-specific innate endowment. The primary objective of the research outlined in this paper is to investigate how such an endowment would influence the acquisition of langage and the dynamics of the repeated cultural transmission of language. To this end, a new connectionist model of the cultural evolution of communication is presented. In this model an individual's innate endowment is considered to be a learning rule with an associated learning bias. The model allows manipulations to be made to this learning apparatus andthe impact of such manipulations on the processes of language acquisition and language evolution to be explored. These investigations reveal that an innate endowment consisting of an ability to read the communicative intentions of others and a bias towards acquiring one-to-one mappings between meanings and signals results in the emergence, through purely cultural processes, of optimal communication. It has previously been suggested that humans possess just such an innate endowment. Properties of human language may therefore best be explained in terms of cultural evolution on an innate substrate.     

Stack-like and queue-like dynamics in recurrent neural networks

What dynamics do simple recurrent networks (SRNs) develop to represent stack-like and queue-like memories? SRNs have been widely used as models in cognitive science. However, they are interesting in their own right as non-symbolic computing devices from the viewpoints of analogue computing and dynamical systems theory. In this paper, SRNs are trained on two prototypical formal languages with recursive structures that need stack-like or queue-like memories for processing, respectively. The evolved dynamics are analysed, then interpreted in terms of simple dynamical systems, and the different ease with which SRNs aquire them is related to the properties of these simple dynamical systems. Within the dynamical systems framework, it is concluded that the stack-like language is simpler than the queue-like language, without making use of arguments from symbolic computation theory.     

Tail-recursive Distributed Representations and Simple Recurrent Networks

Representation poses important challenges to connectionism. The ability to compose representations structurally is critical in achieving the capability considered necessary for cognition. We are investigating distributed patterns that represent structure as part of a larger effort to develop a natural language processor. Recursive auto-associative memory (RAAM) representations show unusual promise as a general vehicle for representing classical symbolic structures in a way that supports compositionality. However, RAAMs are limited to representations for fixed-valence structures and can often be difficult to train. We provide a technique for mapping any ordered collection (forest) of hierarchical structures (trees) into a set of training patterns which can be used effectively in training a simple recurrent network (SRN) to develop RAAM-style distributed representations. The advantages in our technique are three-fold: first, the fixed-valence restriction on structures represented by patterns trained with RAAMs is removed; second, the representations resulting from training correspond to ordered forests of labeled trees, thereby extending what can be represented in this fashion; third, training can be accomplished with an auto-associative SRN, making training a much more straightforward process and one which optimally utilizes the n-dimensional space of patterns.     

An emergent approach to analogical inference

In recent years, a growing number of researchers have proposed that analogy is a core component of human cognition. According to the dominant theoretical viewpoint, analogical reasoning requires a specific suite of cognitive machinery, including explicitly coded symbolic representations and a mapping or binding mechanism that operates over these representations. Here we offer an alternative approach: we find that analogical inference can emerge naturally and spontaneously from a relatively simple, error-driven learning mechanism without the need to posit any additional analogy-specific machinery. The results also parallel findings from the developmental literature on analogy, demonstrating a shift from an initial reliance on surface feature similarity to the use of relational similarity later in training. Variants of the model allow us to consider and rule out alternative accounts of its performance. We conclude by discussing how these findings can potentially refine our understanding of the processes that are required to perform analogical inference.     

由“共享空间”谈谈建筑物内部的空间环境意识

指出环境是一个广义的概念,其由物质环境、精神环境和微观环境所组成.物质环境又包括自然环境和建筑环境.本文通过对"共享空间"概念的探讨,说明了建筑物的内部环境,应使自然环境与精神环境相融合,使其有机、有理、有序,和谐自然.     

Comparison of corrosion rates obtained from laboratory and field data

Generally, corrosion rates for sheet pile walls observed in nature and those obtained in the laboratory are different. In order to compare natural and laboratory corrosion rates, corrosion tests were carried out with an electrochemical corrosion cell. Various mild steel samples which were taken out from different sheet pile structures were examined with synthetic brackish water and synthetic seawater as immersion media. It was ensured that the electrical conductivity and the pH‐values were identical to those of the natural waters from which the sheet pile samples came from. The experimental results indicate that underwater corrosion rates in nature are only about one tenth to one eighth of the laboratory values. The corrosion rates in nature depend on the media and the corrosion zone. Furthermore, in laboratory test procedures, the initial corrosion is always tested whereas in nature a “protecting” layer of rust is formed, that lowers corrosion. Therefore, comparison of the values of the experiments with those from nature should be defined in accordance to age and zone of hydraulic steel structures. As a consequence, a corrosion coefficient with consideration of the age of structures was formed. The introduction of the coefficients's dependence on the lifetime of the construction allows improved corrosion rate predictions when the chemical composition of the immersion media is detected.     

大学语言教育的进场与退场——以语言游戏说为视角

语言的实质是主体问互动的游戏系统.偏离生活方式及师生不对称的关系使语言教育需要一种"格式塔"转变.本文提出了语言教育进场的关键是教育内容的生活化、教育模式的师生互动以及凸显中外思维的异同,以达到学生自由有效进入语言游戏的目的,为语言教育的退场做准备.     

A Recurrent Neural Network that Learns to Count

Parallel distributed processing (PDP) architectures demonstrate a potentially radical alternative to the traditional theories of language processing that are based on serial computational models. However, learning complex structural relationships in temporal data presents a serious challenge to PDP systems. For example, automata theory dictates that processing strings from a context-free language (CFL) requires a stack or counter memory device. While some PDP models have been hand-crafted to emulate such a device, it is not clear how a neural network might develop such a device when learning a CFL. This research employs standard backpropagation training techniques for a recurrent neural network (RNN) in the task of learning to predict the next character in a simple deterministic CFL (DCFL). We show that an RNN can learn to recognize the structure of a simple DCFL. We use dynamical systems theory to identify how network states reflect that structure by building counters in phase space. The work is an empirical investigation which is complementary to theoretical analyses of network capabilities, yet original in its specific configuration of dynamics involved. The application of dynamical systems theory helps us relate the simulation results to theoretical results, and the learning task enables us to highlight some issues for understanding dynamical systems that process language with counters.     

Corrosion informatics: an integrated approach to modelling corrosion

Materials informatics is based on the integration of tools for generating, classifying, analysing and disseminating knowledge in the domain of materials science and engineering, a subset of which includes corrosion science. The purpose of integration is to decrease costs and time associated with research and development. In the context of corrosion, it is proposed that informatics can produce superior decision making tools, decrease risks of failure and improve asset management. An integrated approach is necessary for corrosion because of the multiphysics nature of its contributing mechanisms that include processes at the megascale, materials deformation, electrochemical reactions and fluid dynamics. A hierarchy is introduced that combines models from these subdisciplines with models at more fundamental scientific levels (thermodynamics, microstructural, quantum mechanical and density functional theory/atomistics) and methods for treating uncertainty (Bayesian inference, Monte Carlo and reliability methods). To demonstrate the multiphysics approaches currently available for corrosion prediction, applications are drawn from the recent literature and categorised by topic: general corrosion, localised corrosion and passivity, environmentally assisted cracking, and coatings and inhibitors. Opportunities for integration in each of these subthemes are suggested. Some remarks concerning the integration of probabilistic with deterministic models are made because of the importance of attaching uncertainties to the predictions made by corrosion models, and applying a time-invariant scientific approach to the interpretation of a time-dependent historical record. Finally, a strategy for implementing the integrated approach to corrosion modelling is presented, under the name ‘corrosion informatics’.     

Effect of Tool Wear on Roughness in Hard Turning

This paper attempts to make a contribution to wear estimation of CBN tools when turning hardened steels.It is well known that cutting edge geometry deteriorates with wear. Although many authors have considered tool wear process has a random nature, detailed tool examination has proved that wear has some deterministic features in these processes. Thus, plastic deformation exists in the early stages while gradual abrasion makes the cutting edge recede.On the other hand, it has also been found that there is a good replication of the tool on the roughness profile. Therefore, cutting edge state might be predicted with reasonable accuracy through roughness parameters. This strategy allows fast tool wear estimation by simple roughness measurements using a shop floor instrument.