The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The CasPer algorithm is a constructive neural network algorithm. CasPer creates cascade network architectures in a similar manner to Cascade Correlation. CasPer, however, uses a modified form of the RPROP algorithm, termed Progressive RPROP, to train the whole network after the addition of each new hidden neuron. Previous work with CasPer has shown that it builds networks which generalise better than...
Formal reasoning involves establishment of causal relationships between concepts and a process of chaining through them. Cognitive maps and Fuzzy Cognitive Maps have been proposed as formalisms. In this paper we examine Fuzzy Cognitive Maps with Concepts as nodes and bivalent outputs, and point out inadequacies of such formalism. We propose the introduction of Disconcepts to meet this situation. We...
Artificial neural networks are universal function approximators. The function actually implemented by a network is fully defined by its weights, but the representation in terms of weights is difficult for humans to understand or reason with. It is helpful to efficiently express the network's function in a symbolic form. Golea argues that extracting the minimum disjunctive normal form (DNF) of a network's...
The learning of temporal sequences is an extremely important component of human and animal behaviour. As well as the motor control involved in routine behaviour such as walking, running, talking, tool use and so on, humans have an apparently remarkable capacity for learning (and subsequently reproducing) temporal sequences. A new connectionist model of temporal sequence learning is described which...
A system for acquiring a complete three-dimensional surface description of a complex scene using multiple rangefinders is described. These scenes may contain multiple free-form objects with both convex and concave surface elements. A unique approach for registering each of the views is also proposed. A diamond shaped model with known geometric properties is used to register each of the six views....
This paper explores an approach to robotic automation of mushroom farming, particularly the harvesting process, which involves the application of image processing, 3D range finding and robotic manipulation to realise a system which could make a major contribution to a rapidly growing Australian industry. The main emphasis is on the application of Hough Transform methodology to the selection of appropriate...
The project described in this paper investigates the idea that, in some circumstances, the functions of a complex mechanism can be performed by a large number of simpler units. There are example in nature that support this approach. In the case of locomotion this is seen in the starfish that walks on a large number of tube feet. The structure and control of starfish feet are both simpler than would...
This paper describes the design and construction of a novel robot tactile sensor array. The sensory principle employed is the measurement of diffuse reflected light emanating from a turbid liquid when the liquid is illuminated by a collimated light source. External objects pressed against the sensor vary the thickness of a layer of turbid liquid. Light entering this liquid is back-scattered in proportion...
Real-time computer vision combined with robust gesture recognition provides a natural alternative to traditional computer interfaces. Human users have plenty of experience with actions and the manipulation of objects requiring finger movement. In place of a mouse, users could use their hands to select and manipulate data. This paper presents a first step in this approach using a finger as a pointing...
Knowledge specification can be used as a basis for developing and maintaining simulation systems. This paper presents a knowledge specification methodology based on the temporal logic TLC for solving simulation problems. In this methodology, we build a specific constraint mechanism as a standard prototype for a class of simulation problems which may have some common properties. Such a standard prototype...
Engineering problem solving requires both domain knowledge and an understanding of how to apply that knowledge. While much of the recent work in qualitative physics has focused on building reusable domain theories, there has been little attention paid to representing the control knowledge necessary for applying these models. This paper shows how qualitative representations and compositional modeling...
In order to support verification, validation and analysis of dynamic Operations Research (OR) models a method of testing models against data is required. In the case of the QCM qualitative reasoning system (QRS) this requires an extension to accommodate temporal data streams. This paper examines a number of temporal reasoning methods for QCM. On the basis of this a general methodology for evaluating...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.