- UHRA Home
- Browsing by Author
Browsing by Author "Lane, P.C.R."
Now showing items 1-20 of 33
-
Analysis of Local Search Landscapes for k-SAT Instances
Albrecht, A.; Lane, P.C.R.; Steinhofel, K. (2010)Stochastic local search is a successful technique in diverse areas of combinatorial optimisation and is predominantly applied to hard problems. When dealing with individual instances of hard problems, gathering information ... -
Applying Multi-Criteria Optimisation to Develop Cognitive Models
Lane, P.C.R.; Gobet, F. (Birkbeck, 2005)A scientific theory is developed by modelling empirical data in a range of domains. The goal of developing a theory is to optimise the t of the theory to as many experimental settings as possible, whilst retaining some ... -
Attention mechanisms and component-based face detection.
Han, J.W.; Lane, P.C.R.; Davey, N.; Sun, Yi (IEEE, 2009)Locating and identifying complex objects in a visual scene is a typical problem within the areas of computer vision and image analysis. One technique to minimise the size of image to be identified is to base the classification ... -
Attention Mechanisms in the CHREST Cognitive Architecture
Lane, P.C.R.; Gobet, F.; Smith, R.L. (2009)In this paper, we describe the attention mechanisms in CHREST, a computational architecture of human visual expertise. CHREST organises information acquired by direct experience from the world in the form of chunks. These ... -
Building Classifiers to Identify Split Files.
Green, P. D.; Lane, P.C.R.; Rainer, A.; Scholz, S. (IbaI (Institute of Computer Vision & Applied Computer Sciences), 2009)We apply machine-learning techniques to help automate the process of mining the version history of software projects. Analysis of version histories is important in the study of software evolution. One of the associated ... -
Building models of learning and expertise with CHREST
Lane, P.C.R.; Gobet, F. (Cognitive Science Society, 2010)CHREST (Chunk Hierarchy and REtrieval STructures) is a complete computational architecture implementing processes of learning and perception. CHREST models have successfully simulated human data in a variety of domains, ... -
Checking chess checks with chunks: A model of simple check detection
Smith, R.L.; Gobet, F.; Lane, P.C.R. (Cognitive Science Society, 2009)The procedure by which humans identify checks in check positions is not well understood. We report here our experience in modelling this process with CHREST, a general-purpose cognitive model that has previously successfully ... -
The CHREST architecture of cognition : the role of perception in general intelligence
Gobet, F.; Lane, P.C.R. (Atlantis Press, 2010)This paper argues that the CHREST architecture of cognition can shed important light on developing artificial general intelligence. The key theme is that "cognition is perception." The description of the main components ... -
Chunking mechanisms in human learning
Gobet, F.; Lane, P.C.R.; Croker, S.; Cheng, P. C-H.; Jones, G.; Oliver, I.; Pine, J.M. (2001) -
Combinatorial landscape analysis for k-SAT instances
Albrecht, A.; Lane, P.C.R.; Steinhofel, K. (Institute of Electrical and Electronics Engineers (IEEE), 2008)Over the past ten years, methods from statistical physics have provided a deeper inside into the average complexity of hard combinatorial problems, culminating in a rigorous proof for the asymptotic behaviour of the k-SAT ... -
Combining low-level perception with expectations in CHREST
Lane, P.C.R.; Sykes, A.K.; Gobet, F. (2003)The ability of humans to reliably perceive and recognise objects relies on an interaction between information seen in the visual image and prior expectations. We describe an extension to the CHREST computational model which ... -
Comparing Different Text Similarity Methods
Bao, J.; Lyon, C.; Lane, P.C.R.; Ji, W.; Malcolm, J. (University of Hertfordshire, 2007)This paper reports experiments on a corpus of news articles from the Financial Times, comparing different text similarity models. First the Ferret system using a method based solely on lexical similarities is used, then ... -
Comparing the performance of single-layer and two-layer support vector machines on face detection
Han, J.W.; Lane, P.C.R.; Davey, N.; Sun, Yi. (2007) -
Copy detection in Chinese documents using Ferret
Bao, J.; Lyon, C.; Lane, P.C.R. (2006) -
Copy detection in Chinese documents using the Ferret: a report on experiments
Bao, J.; Lyon, C.; Lane, P.C.R.; Ji, W.; Malcolm, J. (University of Hertfordshire, 2006)The Ferret copy detector has been used for some years on English texts to find plagiarism in large collections of students coursework. This article--reports on extending its application to Chinese, which differs from English ... -
Developing and Evaluating Cognitive Architectures with Behavioural Tests
Lane, P.C.R.; Gobet, F. (2007)We present a methodology for developing and evaluating cognitive architectures based on behavioural tests and suitable optimisation algorithms. Behavioural tests are used to clarify those aspects of an architecture's ... -
Developing reproducible and comprehensible computational models
Lane, P.C.R.; Gobet, F. (2003) -
Discovering predictive variables when evolving cognitive models
Lane, P.C.R.; Gobet, F. (2005)A non-dominated sorting genetic algorithm is used to evolve models of learning from di erent theories for multiple tasks. Correlation analysis is performed to identify parameters which affect performance on specific tasks; ... -
A Distributed Framework for Semi-Automatically Developing Architectures of Brain and Mind
Gobet, F.; Lane, P.C.R. (2005) -
Efficient Search for Plagiarism on the Web
Malcolm, J.; Lane, P.C.R. (2008)Understanding the characteristics of written English allows Internet search for the source of a document to be carried out efficiently. There is a Zipfian distribution of word frequencies in natural language, with some ...