By Topic

Knowledge and Data Engineering, IEEE Transactions on

Issue 2 • Date March-April 2001

Filter Results

Displaying Results 1 - 14 of 14
  • Guest editors' introduction: special section on connectionist models for learning in structured domains

    Publication Year: 2001 , Page(s): 145 - 147
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | PDF file iconPDF (221 KB) |  | HTML iconHTML  
    Freely Available from IEEE
  • Correction to "MPGS: an interactive tool for the specification and generation of multimedia presentations"

    Publication Year: 2001 , Page(s): 334
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (105 KB) |  | HTML iconHTML  

    First Page of the Article
    View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symbolic vs. connectionist learning: an experimental comparison in a structured domain

    Publication Year: 2001 , Page(s): 176 - 195
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2072 KB) |  | HTML iconHTML  

    During the last two decades, the attempts to find effective solutions to the problem of learning any kind of structured information have been splitting the scientific community. A “holy war” has been fought between the advocates of a symbolic approach to learning and the advocates of a connectionist approach. One of the most repeated claims of the symbolic party has been that symbolic methods are able to cope with structured information while connectionist ones are not. However, in the last few years, the possibility of employing connectionist methods for structured data has been widely investigated and several approaches have been proposed. A novel algorithm for learning structured descriptions, ascribable to the category of symbolic techniques, is proposed. It faces the problem directly in the space of graphs by defining the proper inference operators, as graph generalization and graph specialization, and obtains general and consistent prototypes with a low computational cost with respect to other symbolic learning systems. The proposed algorithm is compared with a recent connectionist method for learning structured data (P. Frasconi et al., 1998), with reference to a problem of handwritten character recognition from a standard database on the Web. The orthogonality of the two approaches strongly suggests their combination in a multiclassifier system so as to retain the strengths of both of them, while overcoming their weaknesses. The results on an experimental case study demonstrated that the adoption of a parallel combination scheme of the two algorithms could improve the recognition performance by about 10 percent. A truce or an alliance between the symbolic and the connectionist worlds? View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Incremental syntactic parsing of natural language corpora with simple synchrony networks

    Publication Year: 2001 , Page(s): 219 - 231
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB) |  | HTML iconHTML  

    The article explores the use of Simple Synchrony Networks (SSNs) for learning to parse English sentences drawn from a corpus of naturally occurring text. Parsing natural language sentences requires taking a sequence of words and outputting a hierarchical structure representing how those words fit together to form constituents. Feedforward and simple recurrent networks have had great difficulty with this task, in part because the number of relationships required to specify a structure is too large for the number of unit outputs they have available. SSNs have the representational power to output the necessary O(n2) possible structural relationships because SSNs extend the O(n) incremental outputs of simple recurrent networks with the O(n) entity outputs provided by temporal synchrony variable binding. The article presents an incremental representation of constituent structures which allows SSNs to make effective use of both these dimensions. Experiments on learning to parse naturally occurring text show that this output format supports both effective representation and effective generalization in SSNs. To emphasize the importance of this generalization ability, the article also proposes a short-term memory mechanism for retaining a bounded number of constituents during parsing. This mechanism improves the O(n2) speed of the basic SSN architecture to linear time, but experiments confirm that the generalization ability of SSN networks is maintained View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simple strategies to encode tree automata in sigmoid recursive neural networks

    Publication Year: 2001 , Page(s): 148 - 156
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (348 KB) |  | HTML iconHTML  

    Recently, a number of authors have explored the use of recursive neural nets (RNN) for the adaptive processing of trees or tree-like structures. One of the most important language-theoretical formalizations of the processing of tree-structured data is that of deterministic finite-state tree automata (DFSTA). DFSTA may easily be realized as RNN using discrete-state units, such as the threshold linear unit. A recent result by J. Sima (1997) shows that any threshold linear unit operating on binary inputs can be implemented in an analog unit using a continuous activation function and bounded real inputs. The constructive proof finds a scaling factor for the weights and reestimates the bias accordingly. We explore the application of this result to simulate DFSTA in sigmoid RNN (that is, analog RNN using monotonically growing activation functions) and also present an alternative scheme for one-hot encoding of the input that yields smaller weight values, and therefore works at a lower saturation level View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating linguistic primitives in learning context-dependent representation

    Publication Year: 2001 , Page(s): 157 - 175
    Cited by:  Papers (5)  |  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1696 KB) |  | HTML iconHTML  

    The paper presents an explicit connectionist-inspired, language learning model in which the process of settling on a particular interpretation for a sentence emerges from the interaction of a set of “soft” lexical, semantic, and syntactic primitives. We address how these distinct linguistic primitives can be encoded from different modular knowledge sources but strongly involved in an interactive processing in such a way as to make implicit linguistic information explicit. The learning of a quasi-logical form called context-dependent representation, is inherently incremental and dynamical in such a way that every semantic interpretation will be related to what has already been presented in the context created by prior utterances. With the aid of the context-dependent representation, the capability of the language learning model in text understanding is strengthened. This approach also shows how the recursive and compositional role of a sentence as conveyed in the syntactic structure can be modeled in a neurobiologically motivated linguistics based on dynamical systems rather on combinatorial symbolic architecture. Experiments with more than 2000 sentences in different languages illustrating the influences of the context-dependent representation on semantic interpretation, among other issues, are included View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hyperlog: a graph-based system for database browsing, querying, and update

    Publication Year: 2001 , Page(s): 316 - 333
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (788 KB) |  | HTML iconHTML  

    Hyperlog is a declarative, graph based language that supports database querying and update. It visualizes schema information, data, and query output as sets of nested graphs, which can be stored, browsed, and queried in a uniform way. Thus, the user need only be familiar with a very small set of syntactic constructs. Hyperlog queries consist of a set of graphs that are matched against the database. Database updates are supported by means of programs consisting of a set of rules. The paper discusses the formulation, evaluation, expressiveness, and optimization of Hyperlog queries and programs. We also describe a prototype implementation of the language and we compare and contrast our approach with work in a number of related areas, including visual database languages, graph based data models, database update languages, and production rule systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representation and processing of structures with binary sparse distributed codes

    Publication Year: 2001 , Page(s): 261 - 276
    Cited by:  Papers (6)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (572 KB) |  | HTML iconHTML  

    The schemes for compositional distributed representations include those allowing on-the-fly construction of fixed dimensionality codevectors to encode structures of various complexity. Similarity of such codevectors takes into account both structural and semantic similarity of represented structures. We provide a comparative description of sparse binary distributed representation developed in the framework of the associative-projective neural network architecture and the more well known holographic reduced representations of T.A. Plate (1995) and binary spatter codes of P. Kanerva (1996). The key procedure in associative-projective neural networks is context-dependent thinning which binds codevectors and maintains their sparseness. The codevectors are stored in structured memory array which can be realized as distributed auto-associative memory. Examples of distributed representation of structured data are given. Fast estimation of the similarity of analogical episodes by the overlap of their codevectors is used in the modeling of analogical reasoning both for retrieval of analogs from memory and for analogical mapping View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning distributed representations of concepts using linear relational embedding

    Publication Year: 2001 , Page(s): 232 - 244
    Cited by:  Papers (18)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1720 KB) |  | HTML iconHTML  

    We introduce linear relational embedding as a means of learning a distributed representation of concepts from data consisting of binary relations between these concepts. The key idea is to represent concepts as vectors, binary relations as matrices, and the operation of applying a relation to a concept as a matrix-vector multiplication that produces an approximation to the related concept. A representation for concepts and relations is learned by maximizing an appropriate discriminative goodness function using gradient ascent. On a task involving family relationships, learning is fast and leads to good generalization View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global viewing of heterogeneous data sources

    Publication Year: 2001 , Page(s): 277 - 297
    Cited by:  Papers (51)  |  Patents (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1288 KB) |  | HTML iconHTML  

    The problem of defining global views of heterogeneous data sources to support querying and cooperation activities is becoming more and more important due to the availability of multiple data sources within complex organizations and in global information systems. Global views are defined to provide a unified representation of the information in the different sources by analyzing conceptual schemas associated with them and resolving possible semantic heterogeneity. We propose an affinity based unification method for global view construction. In the method: (1) the concept of affinity is introduced to assess the level of semantic relationship between elements in different schemas by taking into account semantic heterogeneity; (2) schema elements are classified by affinity levels using clustering procedures so that their different representations can be analyzed for unification; (3) global views are constructed starting from selected clusters by unifying representations of their elements. Experiences of applying the proposed unification method and the associated tool environment ARTEMIS on databases of the Italian Public Administration information systems are described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical growing cell structures: TreeGCS

    Publication Year: 2001 , Page(s): 207 - 218
    Cited by:  Papers (18)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (456 KB) |  | HTML iconHTML  

    We propose a hierarchical clustering algorithm (TreeGCS) based upon the Growing Cell Structure (GCS) neural network of B. Fritzke (1993). Our algorithm refines and builds upon the GCS base, overcoming an inconsistency in the original GCS algorithm, where the network topology is susceptible to the ordering of the input vectors. Our algorithm is unsupervised, flexible, and dynamic and we have imposed no additional parameters on the underlying GCS algorithm. Our ultimate aim is a hierarchical clustering neural network that is both consistent and stable and identifies the innate hierarchical structure present in vector-based data. We demonstrate improved stability of the GCS foundation and evaluate our algorithm against the hierarchy generated by an ascendant hierarchical clustering dendogram. Our approach emulates the hierarchical clustering of the dendogram. It demonstrates the importance of the parameter settings for GCS and how they affect the stability of the clustering View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimizing large join queries using a graph-based approach

    Publication Year: 2001 , Page(s): 298 - 315
    Cited by:  Papers (5)  |  Patents (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (544 KB) |  | HTML iconHTML  

    Although many query tree optimization strategies have been proposed in the literature, there still is a lack of a formal and complete representation of all possible permutations of query operations (i.e., execution plans) in a uniform manner. A graph-theoretic approach presented in the paper provides a sound mathematical basis for representing a query and searching for an execution plan. In this graph model, a node represents an operation and a directed edge between two nodes indicates the older of executing these two operations in an execution plan. Each node is associated with a weight and so is an edge. The weight is an expression containing optimization required parameters, such as relation size, tuple size, join selectivity factors. All possible execution plans are representable in this graph and each spanning tree of the graph becomes an execution plan. It is a general model which can be used in the optimizer of a DBMS for internal query representation. On the basis of this model, we devise an algorithm that finds a near optimal execution plan using only polynomial time. The algorithm is compared with a few other popular optimization methods. Experiments show that the proposed algorithm is superior to the others under most circumstances View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustering and classification in structured data domains using Fuzzy Lattice Neurocomputing (FLN)

    Publication Year: 2001 , Page(s): 245 - 260
    Cited by:  Papers (17)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1128 KB) |  | HTML iconHTML  

    A connectionist scheme, namely, σ-Fuzzy Lattice Neurocomputing scheme or σ-FLN for short, which has been introduced in the literature lately for clustering in a lattice data domain, is employed for computing clusters of directed graphs in a master-graph. New tools are presented and used, including a convenient inclusion measure function for clustering graphs. A directed graph is treated by σ-FLN as a single datum in the mathematical lattice of subgraphs stemming from a master-graph. A series of experiments is detailed where the master-graph emanates from a thesaurus of spoken language synonyms. The words of the thesaurus are fed to σ-FLN in order to compute clusters of semantically related words, namely hyperwords. The arithmetic parameters of σ-FLN can be adjusted so as to calibrate the total number of hyperwords computed in a specific application. It is demonstrated how the employment of hyperwords implies a reduction, based on the a priori knowledge of semantics contained in the thesaurus, in the number of features to be used for document classification. In a series of comparative experiments for document classification, it appears that the proposed method favorably improves classification accuracy in problems involving longer documents, whereas performance deteriorates in problems involving short documents View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalization ability of folding networks

    Publication Year: 2001 , Page(s): 196 - 206
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (364 KB) |  | HTML iconHTML  

    The information theoretical learnability of folding networks, a very successful approach capable of dealing with tree structured inputs, is examined. We find bounds on the VC, pseudo-, and fat shattering dimension of folding networks with various activation functions. As a consequence, valid generalization of folding networks can be guaranteed. However, distribution independent bounds on the generalization error cannot exist in principle. We propose two approaches which take the specific distribution into account and allow us to derive explicit bounds on the deviation of the empirical error from the real error of a learning algorithm. The first approach requires the probability of large trees to be limited a priori and the second approach deals with situations where the maximum input height in a concrete learning example is restricted View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.

Aims & Scope

IEEE Transactions on Knowledge and Data Engineering (TKDE) informs researchers, developers, managers, strategic planners, users, and others interested in state-of-the-art and state-of-the-practice activities in the knowledge and data engineering area.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
Jian Pei
Simon Fraser University

Associate Editor-in-Chief
Xuemin Lin
University of New South Wales

Associate Editor-in-Chief
Lei Chen
Hong Kong University of Science and Technology