Search results
1 – 10 of 145
I. ALEKSANDER and M.C. FAIRHURST
Starting with a Moore‐type automaton the bases for a brain‐like sequential machine are laid down. The problem is considered both at the level of a physical structure and a state…
Abstract
Starting with a Moore‐type automaton the bases for a brain‐like sequential machine are laid down. The problem is considered both at the level of a physical structure and a state structure. The logic is cellular and variable to accommodate learning and generalization. It is shown that this structure can “learn to live” in a consistent environment. Concepts such as recognition and recall of environmental events, short‐term memory, data generation (analogous to speech production) and attention are shown to be natural attributes of the model.
This paper describes the use of the MINERVA adaptive computing system in an investigation of feedback in learning networks. The feedback is such as to provide, at the input of the…
Abstract
This paper describes the use of the MINERVA adaptive computing system in an investigation of feedback in learning networks. The feedback is such as to provide, at the input of the network, information regarding the action which the network is taking as a result of a pattern which is input on a different set of terminals. It will be shown that this type of network is very sensitive to small differences between incoming patterns and can provide the basis of a model of animal behaviour such as may be found in frogs when snapping at an insect.
To a certain extent this paper is a reassessment of the above statement. The reassessment consists of a deeper specification of the type of problem which one encounters when…
Abstract
To a certain extent this paper is a reassessment of the above statement. The reassessment consists of a deeper specification of the type of problem which one encounters when trying to formalise not only the nature of a state structure associated with the brain, but also the origins of this state structure. The paper first defines in broad terms the nature of the Structure/Function problem, and then goes on to separate out those parts of a structure which lead to the variational and adaptive nature of the state structure. It argues that the relationship between the structure that leads to adaptation and its embedding in an external environment are crucial areas for further study.
I. Aleksander, W.V. Thomas and P.A. Bowden
The WISARD recognition system invented at Brunei University has been developed into an industrialised product by Computer Recognition Systems under licence from the British…
Abstract
The WISARD recognition system invented at Brunei University has been developed into an industrialised product by Computer Recognition Systems under licence from the British Technology Group. Using statistical pattern classification it already shows great potential in rapid sorting, and research indicates that it will track objects with positional feedback, rather like the human eye.
Image analysis faces data reduction problems when deriving low‐dimensional image spaces (‘perceptual maps’) from multidimensional profile data. The neurocomputing methodology of…
Abstract
Image analysis faces data reduction problems when deriving low‐dimensional image spaces (‘perceptual maps’) from multidimensional profile data. The neurocomputing methodology of Self‐Organizing Maps may contribute to finding a radically parsimonious representation. The principles of SOM methodology are shown in a case study on the company images of nine Austrian tour operators.
Details
Keywords
Roberto Cerchione, Piera Centobelli, Elena Borin, Antonio Usai and Eugenio Oropallo
The effect of digital transition on knowledge management (KM) processes is becoming relevant for companies operating in different industries and the body of literature examining…
Abstract
Purpose
The effect of digital transition on knowledge management (KM) processes is becoming relevant for companies operating in different industries and the body of literature examining this impact is rapidly growing. This paper aims to critically analyse the literature on the impact of digital transition on KM by rethinking the SECI model proposed by Nonaka and proposing the WISED model for the digital knowledge-creating company.
Design/methodology/approach
The systematisation of existing studies on the topic and the analysis of the evolution of knowledge creation process in the era of digital transition was carried out through a bibliometric approach.
Findings
According to the traditional epistemological and ontological dimensions and considering the innovative KM processes identified by this study (i.e. webification, informalisation, systematisation, explicitation and digitalisation), the results highlight how the proposed WISED model can be adopted by organizations to manage knowledge through the use of digital technologies.
Originality/value
Digital transition seems to open up new horizons that can expand the potential use of the WISED model for organisations and society.
Details
Keywords
This paper's aim is to assess the practical advances resulting from progress in artificial intelligence affecting vision‐equipped robots.
Abstract
Purpose
This paper's aim is to assess the practical advances resulting from progress in artificial intelligence affecting vision‐equipped robots.
Design/methodology/approach
A short history of artificial intelligence applied to robotic hand‐eye coordination is followed by a description of some of the milestones in pattern recognition, interfacing, operating systems and programming paradigms. Finally, a range of current‐day practical applications is given, from industrial to student project.
Findings
The paper finds that advances in the speed and robustness of pattern recognition algorithms have been very important in the development of robots that adapt to randomly positioned workpieces. Event‐triggered object oriented programming, wide address buses, smart cameras, ethernet and other standard cables and communications formats, and the ever‐increasing power of computers are also of great practical importance.
Originality/value
The paper contrasts the current state of robotic vision with that 20 years ago.
Details
Keywords
Reviews some of the good reasons for looking to real neural nets for guidance on ways of implementing effective parallel computation. Discusses existing artificial neural nets…
Abstract
Reviews some of the good reasons for looking to real neural nets for guidance on ways of implementing effective parallel computation. Discusses existing artificial neural nets with particular attention to the extent to which they model real neural activity. Indicates some serious mismatches, but shows that there are also important correspondences. The successful applications are to image processing, pattern classification and automatic optimization, in various guises. Reviews important issues raised by extension to the symbolic problem solving of “intellectual” thought, the prime concern of classical AI. These illustrate the importance of recursion, and of a degree of continuity associated with any evolutionary process.
Details
Keywords
Semiotics studies systems of signs. It regards all sign systems as the product of a single human faculty for creating order. The distinction it provides, of signifier, sign and…
Abstract
Semiotics studies systems of signs. It regards all sign systems as the product of a single human faculty for creating order. The distinction it provides, of signifier, sign and signified, can give a more sophisticated and incisive way of differentiating aspects of the sign than can be derived from any other known source. Information science would seem to have some unnoticed affinities with semiotics in its concerns with the retrieval and transmission of material products of the semiotic faculty and with meaning to concept relations. The alignment of information science with the physical sciences and technology has been criticised and its disciplinary identity questioned. Information science would seem to derive what identity it has from a widely shared concern with computer based retrieval of documentary information. However, a unifying principle for the document and the computer has not been enunciated. For semiotics, written language, and computer programs can be comprehended within the analytical category of the signifier. Automata theory regards the computer as a universal information machine and replaces ideas of energy and motion by logical operations. At the level of discourse of logical operations, there is no distinction between a written expression, or program, and the particular information machine specified by that written expression. Elements in linguistics, not registered in the literature of information science, have departed from the received position that written language is simply a representation of speech and have preferred to regard it as an autonomous system of signs. A specific unifying principle for the document and the computer is then the presence of writing. Revealing such a unifying principle indicates that semiotics can clarify significant issues within the established domains of information science.