Narrow Results

Image captioning is a multidisciplinary artificial intelligence (AI) research task that has captures the interest of both image and natural language processing experts. Image captioning is a complex problem as it sometimes requires accessing the information that may not be directly visualized in a given scene. It possibly will require common sense interpretation or the detailed knowledge about the object present in image. In this paper, we have given a method that utilizes both visual and external knowledge from knowledge bases such as ConceptNet for better description the images. We demonstrated the usefulness of the method on two publicly available datasets; Flickr8k and Flickr30k.The results explain that the proposed model outperforms the state-of-the art approaches for generating image captions. At last, we will talk about possible future prospects in image captioning.

Knowledge bases contain specific and general knowledge. In relational database systems, specific knowledge is often represented as a set of relations. The conventional methodologies for centralized database design can be applied to develop a normalized, redundancy-free global schema. Distributed database design involves redundancy removal as well as the distribution design which allows replicated data segments. Thus, distribution design can be viewed as a process on a normalized global schema which produces a collection of fragments of relations from a global database. Clearly, not every fragment of data can be permitted as a relation. In this paper, we clarify and formally discuss three kinds of fragmentations of relational databases, and characterize their features as valid designs, and we introduce a hybrid knowledge fragmentation as the general case. For completeness of presentation, we first show an algorithm for the validity test of vertical fragmentations of normalized relations, and then extend it to the more general case of unbiased fragmentations.

A modularity concept for structuring and developing large logic programs and logical knowledge bases is presented. The concept is motivated from work in the field of algebraic specification, and enforces an extreme modularity discipline that goes beyond the one found in imperative or logic programming languages. As concrete programming languages (respectively knowledge representation formalisms), we consider Horn logic and equational logic programming. We give formal semantics for single modules and discuss correctness and verification issues. Large systems are constructed as interconnections of single modules. We introduce the so-called module operations of composition, actualization, and union, and give results concerning compositionality of semantics and correctness preservation.

Since software engineers spend a large proportion of their time trying to understand computer programs, many tools have been proposed to help them with this task. The construction of such tools raises a series of specification and design issues and requires a careful choice among alternative user interfaces, tool architectures, and knowledge representations. This paper discusses the information needs of software engineers and describes and compares two such tools, the Extensible Dependency Analysis Tool Set (EDATS) and the Inter-Module Code Analysis system (IMCA). A case study is presented showing how each tool would be used to support typical program comprehension tasks. Though the two tools have quite similar objectives, their designs are radically different, leading to interesting contrasts in flexibility and ease of use.

Understanding the web user browsing behaviour in order to adapt a web site to the needs of a particular user represents a key issue for many commercial companies that do their business over the Internet. This paper presents the implementation of a Knowledge Base (KB) for building web-based computerized recommender systems. The Knowledge Base consists of a Pattern Repository that contains patterns extracted from web logs and web pages, by applying various web mining tools, and a Rule Repository containing rules that describe the use of discovered patterns for building navigation or web site modification recommendations. The paper also focuses on testing the effectiveness of the proposed online and offline recommendations. An ample real-world experiment is carried out on a web site of a bank.

Associative Computation is characterized by intertwining of search by content and data parallel computation. An algebra for associative computation is described. A compilation based model and a novel abstract machine for associative logic programming are presented. The model uses loose coupling of left hand side of the program, treated as data, and right hand side of the program, treated as low level code. This representation achieves efficiency by associative computation and data alignment during goal reduction and during execution of low level abstract instructions. Data alignment reduces the overhead of data movement. Novel schemes for associative manipulation of aliased uninstantiated variables, data parallel goal reduction in the presence multiple occurrences of the same variables in a goal. The architecture, behavior, and performance evaluation of the model are presented.

Today's organisations are collecting and storing massive amounts of data from their customer transactions and e-commerce/e-business applications. Many classification algorithms are not scalable to work effectively and efficiently with these very large datasets. This study constructs a new scalable classification algorithm (referred to in this manuscript as Iterative Refinement Algorithm, or IRA in short) that builds domain knowledge from very large datasets using an iterative inductive learning mechanism. Unlike existing algorithms that build the complete domain knowledge from a dataset all at once, IRA builds the initial domain knowledge from a subset of the available data and then iteratively improves, sharpens and polishes it using the chucks from the remaining data. Performance testing of IRA on two datasets (one with approximately five million records for a binary classification problem and another with approximately 600 K records for a seven-class classification problem) resulted in more accurate domain knowledge as compared to other prediction methods including logistic regression, discriminant analysis, neural networks, C5, CART and CHAID. Unlike other classification algorithms whose performance and accuracy deteriorate as data size increases, the efficacy of IRA improves as datasets become significantly larger.

This paper addresses a key interest in Keith Pavitt's later work; the organisational arrangements for co-ordinating technological knowledge. It also concurs with Pavitt's insistence on the constraints on managerial agency and his nihilistic amusement at frustrated plans. The paper considers Pavitt's conceptualisation of knowledge bases as technical disciplines and argues that there is an inconspicuous sub-level of specialised knowledge base associated with tools, products, project experience and requirements that may hamper the intents of higher-level organisation design.

Two contrasting case studies are analysed of organisations attempting to manage transitions that are aimed at improving co-ordination processes. The first has moved from organisation around functional disciplines to product-based, cross-functional teams, while the second has done the reverse. The paper reviews the effects of these opposing organizational solutions on the processes of knowledge integration within the firms, the effects on communities of practice and the ways in which the systems have developed and adapted in response to the reorganisations. The paper challenges some of the simplistic prescriptions offered in the literature and provides further fuel for the debates over organisation design and the knowledge integration task.

In the context of semantic knowledge bases, among the possible problems that may be tackled by means of data-driven inductive strategies, one can consider those that require the prediction of the unknown values of existing numeric features or the definition of new features to be derived from the data model. These problems can be cast as regression problems so that suitable solutions can be devised based on those found for multi-relational databases. In this paper, a new framework for the induction of logical regression trees is presented. Differently from the classic logical regression trees and the recent fork of the terminological classification trees, the novel terminological regression trees aim at predicting continuous values, while tests at the tree nodes are expressed with Description Logic concepts. They are intended for multiple uses with knowledge bases expressed in the standard ontology languages for the Semantic Web. A top-down method for growing such trees is proposed as well as algorithms for making predictions with the trees and deriving rules. The system that implements these methods is experimentally evaluated on ontologies selected from popular repositories.

Florida’s approach to urban and regional development focusing on innovation and the creative class spurred an awareness of how space and particularly soft locational characteristics are related to economic performance. In the light of two decades of theoretical discussions and empirical findings, this chapter reflects on three aspects of Florida’s creative class approach. First, the definition and measurement of the creative class, second, the role of contextual differences for the outcome of the relations that are argued in the approach, and third, a discussion of what has changed in the last 20 years since Florida launched his book and to what extent the arguments are valid today with a specific reference to Europe.

Associative Computation is characterized by intertwining of search by content and data parallel computation. An algebra for associative computation is described. A compilation based model and a novel abstract machine for associative logic programming are presented. The model uses loose coupling of left hand side of the program, treated as data, and right hand side of the program, treated as low level code. This representation achieves efficiency by associative computation and data alignment during goal reduction and during execution of low level abstract instructions. Data alignment reduces the overhead of data movement. Novel schemes for associative manipulation of aliased uninstantiated variables, data parallel goal reduction in the presence multiple occurrences of the same variables in a goal. The architecture, behavior, and performance evaluation of the model are presented.

Our knowledge of the biological mechanisms underlying complex human disease is largely incomplete. While Semantic Web technologies, such as the Web Ontology Language (OWL), provide powerful techniques for representing existing knowledge, well-established OWL reasoners are unable to account for missing or uncertain knowledge. The application of inductive inference methods, like machine learning and network inference are vital for extending our current knowledge. Therefore, robust methods which facilitate inductive inference on rich OWL-encoded knowledge are needed. Here, we propose OWL-NETS (NEtwork Transformation for Statistical learning), a novel computational method that reversibly abstracts OWL-encoded biomedical knowledge into a network representation tailored for network inference. Using several examples built with the Open Biomedical Ontologies, we show that OWL-NETS can leverage existing ontology-based knowledge representations and network inference methods to generate novel, biologically-relevant hypotheses. Further, the lossless transformation of OWL-NETS allows for seamless integration of inferred edges back into the original knowledge base, extending its coverage and completeness.