School of Computing, Information Technology and Engineering

Journals

1. Miao Kang and Dominic Palmer-Brown. A Modal Learning Adaptive Function Neural Network Applied to Handwritten Digit Recognition. Accepted for Information Sciences, 2008.
2. Helen Donelan, Colin Pattinson, Dominic Palmer-Brown (2006).The Analysis of User Behaviour of a Network Management Training Tool using a Neural Network, Volume 3, Number 5, 2006. Systemics, Cybernetics and Informatics
3. Dominic Palmer-Brown and Sin Wee Lee. Continuous Reinforced Snap-Drift Learning in a Neural Architecture for Proxylet Selection in Active Computer Networks. International Journal of Simulation Systems, Science & Technology. Special Issue on: Intelligent Systems. Volume 6, Number 9, August 2005
4. H. Donelan, C. Pattinson, D. Palmer-Brown and S.W. Lee. The Analysis of Network Managers' Behaviour. International Journal of Simulation Systems, Science & Technology. Special Issue on: Intelligent Systems. Volume 6, Number 9, August 2005
5. Sin Wee Lee, Dominic Palmer-Brown, Christopher M. Roadknight (2004). Performance-guided neural network for rapidly self-organising active network management. [Invited paper] Neurocomputing, 61C: 5 - 20.
6. C. Roadknight, D. Palmer-Brown, D. Al-Dabass (2003). Simulation of Correlation Activity Pruning Methods to Enhance Transparency of ANNs. Int. Journal of Simulation, Science, Systems and Technology 4(2): 68-74.
7. Palmer-Brown D, Tepper J, Powell H. Connectionist Natural Language Parsing. Trends in Cognitive Sciences, 6, 10, 2002.
8. Tepper J, Powell H, Palmer-Brown D. A corpus-based connectionist architecture for large-scale natural language parsing. Connection Science 14, 2, 2002.
9. Ball G, Palmer-Brown D, Fuhrer J, Skarby L, Gimeno B and Mills G. Identification of non-linear influences on the seasonal ozone dose response of sensitive and resistant clover clones using artificial neural networks. Ecological Modelling, 2000.
10. Benton J, Fuhrer J, Gimeno B, Skarby L, Palmer-Brown D, Ball G, Roadknight C, and Mills G. The widespread occurrence of injury on crops caused by ambient ozone episodes in Europe. Agriculture, Ecosystems and Environment 2000.
11. G Mills, G Ball, D Palmer-Brown et al. "Identifying factors which modify the effects of ambient ozone on white clover (Trifolium repens L.) in Europe". Environmental Pollution.103, 7-16 , 1998.
12. Roadknight C, Balls G, Mills G, Palmer-Brown D (1997). Modeling Complex Environmental Data. IEEE Trans. on Neural Networks, 8, 4, July 1997.
13. Callan R, Palmer-Brown D. (1997). (S)RAAM: An Analytical Technique for Fast and Reliable Derivation of Connectionist Symbol Structure Representations. Connection Science 9, 2, 1997, pp. 139-159.
14. G Balls, D Palmer-Brown, G. Sanders (1996) “The Use of Artificial Neural Networks to Model Plant Environment Interactions” Pesticide Science, vol 46,1996, pp. 280-281.
15. H M Powell, D Palmer-Brown (1996) "Computer-Aided Learning in Computing" in Innovation: Teaching and Learning Journal of The Nottingham Trent University, Issue 1, July 1996, ISBN 1364-0607
16. G Balls, D Palmer Brown, A H Cobb, G E Sanders (1995). "Towards unravelling the complex interactions between microclimate, ozone dose and ozone injury in clover”. Journal of Water, Air and Soil Pollution, 85, pp. 1467-1472.

Recent Conference Proceedings

1. Ekpenyong, F and Palmer-Brown, D. (2007) Updating of Road Network Databases: Spatio-temporal trajectory grouping using snap-drift neural network. Proc. Int Conf on Engineering Applications of Neural Networks, EANN2007.
2. Kang, M and Palmer-Brown, D. (2007) Snap-drift Adaptive Function Neural Network for Pen-based Recognition of Handwritten Digits. Proc. Int Conf on Engineering Applications of Neural Networks, EANN2007.
3. Ekpenyong, F., Brimicombe, A., and Palmer-Brown, D. (2007) Updating Road Network Databases: Road Segment Grouping Using Snap-Drift Neural Network. Geograpical Information Science Research Conference (GISRUK07).
4. Lee, S. W. and D. Palmer-Brown (2006). Phonetic Feature Discovery in Speech using Snap-Drift. International Conference on Artificial Neural Networks (ICANN'2006). Athens, Greece, 10th - 14th September 2006, S. Kollias et al. (Eds.): ICANN 2006 pp. 952 – 962.
5. Lee, S. W. and D. Palmer-Brown (2006). Modal Learning in A Neural Network. 1st Conference in Advances in Computing and Technology (London, United Kingdom, 24th January), pp. 42 - 47.
6. Miao Kang and Dominic Palmer-Brown. A Multilayer ADaptive FUnction Neural Network (MADFUNN) for Analytical Function Recognition. Accepted for Intenational Joint Conference on Artificial Neural Networks (2006).
7. Lee, S. W. and D. Palmer-Brown (2005). Phrase Recognition using Snap-Drift Learning Algorithm.The International Joint Conference on Neural Networks (IJCNN’2005) (Montreal, Canada, 31st July – 4th August).
8. Dominic Palmer-Brown and Sin Wee Lee. Snap-drift Learning for Phrase Recognition. Intenational Joint Conference on Artificial Neural Networks. 2005.
9. Dominic Palmer-Brown and Miao Kang. An Adaptive Function Neural Network (ADFUNN) for Phrase Recognition. Intenational Joint Conference on Artificial Neural Networks. 2005.
10. Dominic Palmer-Brown and Miao Kang. ADFUNN: An Adaptive Function Neural Network. Int. Conf. on Adaptive and Natural Computing Algorithms (2005).
11. Miao Kang and Dominic Palmer-Brown. An Adaptive Function Neural Network (ADFUNN) for Function Recognition. Proc. Advances in Computational Intelligence and Security (2005).
12. Lee, S. W.; D. Palmer-Brown and C. M. Roadknight. (2004). “Snap-drift: Performance-guided Neural Network for Continuous Learning.” Special House of Commons’ Reception for Younger Researchers, House of Commons (London, UK, 15th September).
13. D. Palmer-Brown, S W Lee, and C. M. Roadknight (2004). Reinforced Snap-Drift Learning for Proxylet Selection in Active Computer Networks, International Joint Conference on Neural Networks (IJCNN’2004), Budapest, Hungary, July 2004.
14. S. W. Lee, D. Palmer-Brown and C. M. Roadknight. (2004). Continuous Reinforced Snap-Drift Learning in a Neural Architecture for Proxylet Selection in Active Computer Networks. Proceeding of The 18th European Simulations Multiconference (ESM’2004), Magdeburg, Germany, 13th – 16th June, pp 136 – 142.
15. H. Donelan, C. Pattinson, D. Palmer-Brown and S. W. Lee. (2004). The Analysis of Network Manager’s Behaviour using a Self-Organising Neural Networks, Proceeding of The 18th European Simulations Multiconference (ESM’2004) , Magdeburg, Germany, 13th – 16th June, pp 111 – 116.
16. H Donelan, C Pattinson, D Palmer-Brown (2004). The Analysis of User Behaviour of a Network Management Training Tool Using a Neural Network. The International Conference on Education and Information Systems: Technologies and Applications (EISTA 2004), Orlando, Florida, USA, in July 21-25, 2004. [Best Paper Award].
17. D. Palmer-Brown, S. W. Lee, J. Tepper and C. M. Roadknight (2003). Fast Learning Neural Nets with Adaptive Learning Styles (Invited Paper), Proceeding of the 17th European Simulation Multiconference (ESM'2003), The Nottingham Trent University, Nottingham, UK, 9th - 11th June 2003, pp 118 – 123.
18. S. W. Lee, D. Palmer-Brown, J. A. Tepper and C. M. Roadknight (2003). Snap-Drift: Real-time, Performance-guided Learning, International Joint Conference on Neural Networks (IJCNN’2003), Portland, Oregon, 20th - 24th July 2003.
19. Sin Wee Lee, D Palmer-Brown, J Tepper. Performance-guided neural network for self organising network management. London Communications Symposium, UCL, 2002.
20. Sin Wee Lee, D Palmer-Brown, J Tepper, C Roadknight. Performance-guided Neural Network for Rapidly Self-Organising Active Network Management. Proc. of Hybrid Intelligent Systems 2002 (HIS2002). [Best Paper Award].

Collaborations and Funding:

1. 1993-7 JISC HEFCE, 45K, Generic Approach to the Design and Implementation of Intelligent User Interfaces. D.Palmer-Brown, H Powell;
2. 1993-6 Department of Environment, 250K, Effect of Air Pollution on Crops (neural network computer modelling for intelligent data analysis). G Sanders (Life Sciences), D Palmer-Brown (Computing);
3. 1997-2000 NERC/Department of Environment (sub-contract from Institute of Terrestrial Ecology), 48K, continuation of the above project. D Palmer-Brown. G Ball [Making NTU Dept of Computing The Data Processing Centre for UN Economic Commision for Europe Data from 15 countries];
4. 2000-2003, CASE Studentship, British Telecom Research Labs, 19k, Neural Nets for Active Network Adaptation. D Palmer-Brown, Sin Wee Lee;
5. 2003-2005, Senior BT Visiting Research Fellow (Chris Roadknight), funded by BT/DTI to work in the School of Computing at Leeds Metropolitan University.

Journals

1. Ball G, Palmer-Brown D, Fuhrer J, Skarby L, Gimeno B and Mills G. Identification of non-linear influences on the seasonal ozone dose response of sensitive and resistant clover clones using artificial neural networks. Ecological Modelling, 2000.
2. Benton J, Fuhrer J, Gimeno B, Skarby L, Palmer-Brown D, Ball G, Roadknight C, and Mills G. The widespread occurrence of injury on crops caused by ambient ozone episodes in Europe. Agriculture, Ecosystems and Environment 2000.
3. G Mills, G Ball, D Palmer-Brown et al. "Identifying factors which modify the effects of ambient ozone on white clover (Trifolium repens L.) in Europe". Environmental Pollution.103, 7-16 , 1998.
4. Roadknight C, Balls G, Mills G, Palmer-Brown D (1997). Modeling Complex Environmental Data. IEEE Trans. on Neural Networks, 8, 4, July 1997.
5. Callan R, Palmer-Brown D. (1997). (S)RAAM: An Analytical Technique for Fast and Reliable Derivation of Connectionist Symbol Structure Representations. Connection Science 9, 2, 1997, pp. 139-159.
6. G Balls, D Palmer-Brown, G. Sanders (1996) “The Use of Artificial Neural Networks to Model Plant Environment Interactions” Pesticide Science, vol 46,1996, pp. 280-281.
7. H M Powell, D Palmer-Brown (1996) "Computer-Aided Learning in Computing" in Innovation: Teaching and Learning Journal of The Nottingham Trent University, Issue 1, July 1996, ISBN 1364-0607
8. G Balls, D Palmer Brown, A H Cobb, G E Sanders (1995). "Towards unravelling the complex interactions between microclimate, ozone dose and ozone injury in clover”. Journal of Water, Air and Soil Pollution, 85, pp. 1467-1472.

Themed Conference Papers (most recent last)

Artificial Neural Networks for Natural Language Engineering and Knowledge Extraction

1. R E Callan, D Palmer-Brown. (1995) “Analytical Derivation of a (S)RAAM”. Proc of International Conference on Artificial Neural Networks, ICANN ‘95, Neuronimes ‘95, Maison de la Chimie, October 9-13 1995, Paris, ISBN 2 910085 18 X.
2. J Tepper, H Powell, D Palmer-Brown (1995a) "Ambiguity Resolution in a Connectionist Parser" The Cognitive Science of Natural Language Processing, July 5-7 1995, Editor A I C Monaghan, Natural Language Group.
3. J A Tepper, H Powell, D Palmer-Brown (1995b) Integrating Symbolic and Subsymbolic Architectures for Parsing Arithmetic Expressions and Natural Language Sentences” Proceedings of 3rd SNN Neural Network Symposium, Nijmegen, Sept 1995, pp 81-84, Eds Bert Kappen and Stan Gielen, ISBN 3-540-19992-6.
4. R E Callan, D Palmer Brown (1996). “Analytical Technique for Deriving Connectionist Representations of Symbol Structures” . Proc. of Artificial Neural Networks (ICANN 96), Bochum, Germany, July 1996, Springer Press, pp 341-346, ISBN 3 540 61510 5.
5. S Zhang, H Powell, D Palmer-Brown (1999). Keyword Extraction using Artificial Neural Networks. 10th Conf. On Computational Linguistics in the Netherlands (CLIN99).
6. S. Zhang, D Palmer-Brown, H Powell. Keyword Extraction by Stemming and Sense Information using Neural Networks. Proc. of Int. Conf. On Artificial Intelligence, IC-AI'01, Las Vegas, 2001.
7. De Boni M, Grierson A, Moore D, Palmer-Brown D, Proposed enhancements to a Debating System. ECAI 2000 workshop on Computational Dialectics.
8. Zhang, Powell, Palmer-Brown. Methods for concept extraction using ANNs and stemming analysis and their portability across domains. Proc. of NLPNN2001.
9. Tepper, Powell, Palmer-Brown. Corpus-based Connectionist Parsing. Proc. of NLPNN2001.

Applied AI and Computer Aided Learning

1. D Palmer Brown, H M Powell, B Hanson (1993) "Computer Aided Teaching of Real time Processing, Computing Curriculum" Development and Delivery All Ireland Conference, Dublin City University, September 1993. In CTI, Computers in Teaching Initiative, No 4, 1993-94, Eds. Sylvia Alexander & Arnold McAlpin, pp113-117.
2. D Palmer Brown, H M Powell (1994) "Computer aided Learning to Enhance the Teaching of Computer Hardware" in Alternative Approaches to Teaching Engineering Volume II, Ed Ivan Moore and Kate Exley, The UK Universities' and Colleges' Staff Development Agency 1994, pp 95-99,ISBN 1 85889 023 3.
3. H M Powell, D Palmer-Brown, B Hanson (1994) "Approaches to Teaching Sequential Logic" Proc of 29th Annual Int Conf of the Association for Educational and Training Technology: Computer-Assisted and Open Access Education, Napier University, Edinburgh, April 1994, Eds Percival, Land and Novill, pp 316-317, ISBN 0 7494 1414 6.
4. G Long, H Powell, D Palmer Brown (1995a) "A Syntax Free NLP Interface for an Intelligent Environment " Proc of CSNLP'95 Cognitive Science - Natural Language Processing, University of Dublin, 5-7 July 1995, Editor A I C Monaghan, pp 1-8.
5. G Long, M Edwards, H Powell, D Palmer Brown. (1995b) "Natural Language Interaction as a Vehicle for Learning in a Hypermedia Environment". Proc. of 1st International Workshop on Intelligence and Multimodality in Multimedia Interfaces (IMMI-1), University of Edinburgh, 13-14
6. M Edwards, H Powell, D Palmer Brown (1995) "A Hypermedia-based Tutoring & Knowledge Engineering System". Proceedings of ED-MEDIA '95, World Conf. on Educational Multimedia and Hypermedia, pp 199-204, Ed Hermann Maurer,ISBN 1-880094-15-0.
7. M Edwards, H Powell, D Palmer-Brown (1996) "A Comparative Evaluation of a Natural Language Exploration Tool within a Hypermedia Environment" ICTAI'96: IEEE Int. Conf. on Tools with Artificial Intelligence, Toulouse, France.

Artificial Neural Networks for Data Analysis

1. D Palmer-Brown. A Neural Net for Locating Eyes in Grey Level Images of Faces. Proc. of 1st Australian Conf. on Neural Networks. 1990.
2. D Palmer-Brown (1992) High Speed Learning in a Supervised, Self Growing Net. Proc of Int Conf on Artificial Neural Networks (ICANN-92), Vol 2, Eds Igor Aleksander and John Taylor, pp 1159-1162, ISBN 0 444 894888, 4-7 Sept 1992, Brighton,
3. Roadknight C, Palmer-Brown D, Sanders G. (1995). “Learning the Equations of Data”. Proc. 3rd Annual SNN Symposium on Neural Networks. Kappen, Gielen (Eds). Springer-Verlag pp. 253-257.
4. S Barker, H Powell, D Palmer-Brown. High Speed Face Location at Optimal Resolution. Proc. World Congress on Neural Networks. 1995. ISBN 1-56321-196-4.
5. S Barker, H Powell, D Palmer-Brown. Size Invariant Attention Focusing (with ANNs). Proc. of Int. Symposium on Multi-Technology Information Processing. 1996.
6. Benton J, Fuhrer J, Gimeno B, Skarby L, Balls G, Palmer-Brown D, Roadknight C and Sanders G. 1996. The International Crops Programme and critical levels of ozone for injury development. In Exceedences of Critical Loads and Levels. Eds. M Knoflacher, J Scneider and G Soja. Umweltbundesamt (Federal Environment Agency) Wein, Austria, pp 97-112.
7. Roadknight C, Palmer-Brown D, and Mills G. (1997). Correlated Activity Pruning. Proc. of 5th Fuzzy Days, Dortmund, April 28-30th, 1997. Lecture Notes in Computer Science, 591-592. Springer Verlag.
8. Roadknight C, Palmer-Brown D, Mills G. (1997). The Analysis of Artificial Neural Network Data Models. Lecture Notes in Computer Science 1280. Eds. Liu, Cohen, Berthold.
9. Ball G, Palmer-Brown D, and Mills G. A Comparison of Artificial Neural Networks and Conventional Statistical Techniques for Analysing Environmental Data. Proc. of Int. Workshop on The Application of Artificial Neural Networks to Ecological Modelling, Toulouse, Springer-Verlag. 1999.
10. Roadknight C, D Palmer-Brown, D. Al-Dabass, "Simulation of Correlation Activity Pruning Methods to Enhance Transparency of ANNs", UKSIM2001, Conf. Proc. of the UK Simulation Society , Emmanuel College, Cambridge, 28-30 March 2001, pp56-62, ISBN 1-84233-026-8.

1. Editor, Trends in Cognitive Sciences 2000-2; Associate Editor, Int Conf on Artificial Intelligence 2000. Co-editor, Advances in Computing and Technology, UEL, 2006 and 2007; and International Conference on Global eSecurity, 2006, 2007, 2008. Guest Editor, Special Issue on Industrial Applications, Neurocomputing, 2009.
2. Invited lectures: Café Scientifique 1999, 2001, on AI and the Future; Dortmund University, 2003: Neural Networks; IT Center, Dortmund, 2003: Neural Networks; ESM2003 Keynote Plenary on Fast Learning Neural Nets; Inuagural lecture on Neurocomputing, Leeds Met, 2004; Keynote on Modal Learning Neural Networks, 10th Int. Conf. on Engineering Applications of Neural Networks, EANN 2007; Keynote on Modal Learning Neural Networks, WSEAS Int Conf on Neural Networks, May 2008. Keynote on Modal and Virtual Learning at 5th IFIP Conference on Artificial Intelligence Applications & Innovations, AIAI 2009.
3. Organiser: UN ECE Workshop on Neural Networks for Data Analysis, Holland, 1998; Session organiser: Neural Networks for Data Analysis and Knowledge Engineering, ICAI’00; Track and session organiser: Artificial Intelligence, ESM2003; General Co-Chair, Int. Conf. on Global eSecurity, ICGeS06 and Senior Programme Committee, ICGeS07. International Organising Committees: ICAI’00, ESM2003, ESM2004, Computational Intelligence and Security, CIS’06 and CIS’07, 10th Int. Conf. on Engineering Applications of Neural Networks, 2007. 
4. Reviewing and refereeing for journals: Trends in Cognitive Sciences; Brain and Behavioural Sciences; Bioinformatics; Software Quality. Reviewer for NERC, BBSRC on neural computing proposals. Reviewing/refereeing for conferences: International Conference on Artificial Intelligence 2000 (ICAI’00), European Simulation Multiconference 2003 (ESM2003), International Conference on Cognitive Science 2004; 10th Int. Conf. on Engineering Applications of Neural Networks, 2007. 
5. Founding Chair, Café Scientifique, Nottingham, 1999-2001.
6. Founder and Leader of the Intelligent Systems and Learning Environments (ISLE), 2000-1, and Computational Intelligence (2003-5) research groups, Leeds Metropolitan University; 
7. External examiner, Northampton University, Computing degrees, 2006- present
8. External advisor to: Bedfordshire University, validation of computing masters programmes, 2007; London Metropolitan University, approval of new computing undergraduate and postgraduate programmes, 2008; Canterbury Christ Church University, approval of masters in computing, 2008.
9. PhD examining: Nottingham Trent, Electronic Engineering; Nottingham Trent, Computing; Leeds Metropolitan University, Information Management; Sunderland University, Computing; Northampton University, Engineering and Technology; University of the Arts, London; Computing and Technology, University of East London.
10. Supervision of research fellows, assistants, and PhD supervision (12 PhDs to completion). Currently supervising 7 PhDs at Leeds Met, UEL School of Comptuing and Technology and SMARTlab Digital Media Centre.

Connectionist natural language parsing. Dominic Palmer-Brown, Jonathan A Tepper and Heather M. Powell.

The key developments of two decades of connectionist parsing are reviewed. The parsers are assessed according to their ability to learn syntactic structures without the help of symbolic grammar rules. The review also considers the extent to which connectionist parsers are plausible models of human sentence processing and how well they account for the psycholinguistic data. The level of realism, the extent of modularity, and the syle of distributed or localist processing employed are considered as important factors in connectionist parsing.

Performance-guided neural network for rapidly self-organising active network management. Sin Wee Lee,, Dominic Palmer-Brown, Christopher M. Roadknight

We present a neural network for real-time learning and mapping of patterns using an external performance indicator. In a non-stationary environment where new patterns are continually introduced, the learning method utilises a novel snap-drift algorithm based on fast, convergent, minimalist (snap) learning when the overall network performance is poor and slower, cautious (drift) learning when performance is good. Snap is based on a modified form of Adaptive Resonance Theory; and drift is based on Learning Vector Quantization (LVQ). The two forms are combined within a quasi-unsupervised learning system that shifts its learning style whenever it receives a change in performance feedback. The learning is capable of rapid re-learning and re-stabilisation, according to changes in external feedback or input patterns. We have used this algorithm in the design of a modular neural network system, known as Performance-guided Adaptive Resonance Theory. Simulation results show that the system discovers alternative solutions in response to significantly changed input patterns and/or the operating environment, which may require the patterns to be treated differently over time. The simulations involve attempting to optimise the selection of network services in a non-stationary, real-time active computer network environment, in which many changing temporal factors influence the required selections.

ADFUNN: An Adaptive Function Neural Network. Dominic Palmer-Brown and Miao Kang

An adaptive function neural network (ADFUNN) is introduced. It is based on a linear piecewise neuron activation function that is modified by a novel gradient descent supervised learning method. This ∆f process is carried out in parallel with the traditional ∆w process. Linearly inseparable problems can be rapidly learned with ADFUNN, without the need for a multilayer structure (hidden layers). The well known Iris dataset classification problem is learned as an example. An additional benefit of ADFUNN is that the learned functions can support intelligent data analysis.

Reinforced Snap-Drift Learning for Proxylet Selection in Active Computer Networks. Dominic Palmer-Brown, Sin Wee Lee and Chris Roadknight.

A new continuous learning method is applied to the problem of optimising the selection of services in a computer network environment. The learning is an enhanced version of the snap-drift algorithm for non-stationary environments. Snap is based on ART, and drift on LVQ Quantization. The algorithm swaps its learning style between the two modes when performance levels decline, but maintains the same learning style during episodes of improved performance. Reinforcement also occurs since learning is enabled with a probability that increases/decreases in proportion to declining/improving performance. The method rapidly re-learns and simulations demonstrate stability, combined with the ability to discover solutions in response to new performance requirements.

A corpus-based connectionist architecture for large-scale natural language parsing. Jonathan Tepper, Heather Powell, and Dominic Palmer-Brown

We describe a deterministic shift-reduce parsing model that combines the advantages of connectionist networks with those of traditional symbolic models for parsing realistic sub-domains of natural language. It is a modular system that learns to annotate natural language texts with syntactic structure. The parser acquires its linguistic knowledge directly from pre-parsed sentence examples extracted from an annotated corpus. The connectionist modules enable the automatic learning of linguistic constraints and provide a distributed representation of linguistic information that exhibits tolerance to grammatical variations. The inputs and outputs of the connectionist modules represent symbolic information which can be easily manipulated and interpreted, and provides the basis for organising the parse. In contrast with previous approaches to syntactic parsing with connectionist networks, the corpus-based model exhibits high levels of syntactic generalisation that allows for a wide-ranging coverage of commonly used English language. An important feature of the model is that it is adaptable to the grammatical framework of the training corpus and so the approach is not limited to a particular grammatical formalism.

The Analysis of User Behaviour of a Network Management Training Tool using a Neural Network. Helen Donelan, Colin Pattinson, Dominic Palmer-Brown

A novel method for the analysis and interpretation of data that describes the interaction between trainee network managers and a network management training tool is presented. A simulation based approach is currently being used to train network managers, through the use of a simulated network. The motivation is to provide a tool for exposing trainees to a life like situation without disrupting a live network. The data logged by this system describes the detailed interaction between trainee network manager and simulated network. This work provides an analysis of the interaction data that enables an assessment of the capabilities of the trainee network manager and aids understanding of how the network management tasks are being approached. A neural network architecture is implemented in order to perform an exploratory data analysis of the interaction data. The neural network employs a novel form of continuous self-organisation to discover key features in the data and thus provide new insights into the learning and teaching strategies employed by the trainees.

Diagnostic Feedback tool for Virtual Learning Environment. Dominic Palmer-Brown (leader), Sin Wee Lee, Alor Edoh, Vishal Kanaber and Mike Kretsis

Snap-drift Neural Networks (SDNNs), which employ the complementary concepts of fast, minimalist (snap) learning and slow (drift towards the input pattern) learning is used for the automatic generation of diagnostic feedback for students in an e-learning environment. By discovering the hidden features in the students' responses, such as those to multiple choice questions, typical error patterns, and by taking into account levels of question difficulty, and linguistic (phrasal and lexical) analysis/recognition in short answers, the SDNN will select the most appropriate feedback mix from a corpus. This system will be tested on 'live' students to facilitate automatic diagnosis of deficits in areas of knowledge and to provide specific guidance.