- UHRA Home
- Browsing by Author
Browsing by Author "Adams, R.G."
Now showing items 61-80 of 116
-
High performance associative memory models and symmetric connections
Davey, N.; Adams, R.G.; Hunt, Stephen (2000)Two existing high capacity training rules for the standard Hopfield architecture associative memory are examined. Both rules, based on the perceptron learning rule produce asymmetric weight matrices, for which the simple ... -
High performance associative memory models and weight dilution
Davey, N.; Adams, R.G.; Hunt, S. (2001)The consequences of diluting the weights of the standard Hopfield architecture associative memory model, trained using perceptron like learning rules, is examined. A proportion of the weights of the network are removed; ... -
High performance associative memory models with low wiring costs
Calcraft, L.; Adams, R.G.; Davey, N. (2006) -
Human shape recognition from snakes using neural networks
Tabb, Ken; Davey, N.; George, S.; Adams, R.G. (Institute of Electrical and Electronics Engineers (IEEE), 1999)This paper documents experiments which have been carried out with several neural network systems designed to categorise pedestrian shapes from non-pedestrian shapes. Active Contour models (‘Snakes’) [1] have been used to ... -
A Hybrid Detection and Classification System for Human Motion Analysis
Tabb, Ken; Davey, N.; Adams, R.G.; George, S. (Springer Nature, 2002) -
Identifying binding sites in sequential genomic data
Robinson, M.; Gonzalez Castellano, C.; Adams, R.G.; Davey, N.; Sun, Yi. (2007) -
Identifying word boundaries in handwritten text
Sun, Yi.; Butler, T.; Shafarenko, A.; Loomes, M.J.; Adams, R.G.; Davey, N. (2004) -
iHARP a Multiple Instruction Issue Processor Chip Incorporating RISC and VLIW Design Features
Trainis, S.A.; Findlay, P.; Steven, G.B.; Adams, R.G.; McHale, D. (1992)RISC (Reduced Instruction Set Computers) processors have established an impressive performance standard by executing one instruction in each processor cycle. More recently, VLIW (Very Long Instruction Word) and superscalar ... -
iHarp: a Multiple Instruction Issue Processor
Steven, G.B.; Adams, R.G.; Findlay, P.; Trainis, S.A. (1992) -
Integrating genomic binding site predictions using real-valued meta classifiers
Sun, Yi.; Robinson, M.; Adams, R.G.; Kaye, Paul H.; Te Boekhorst, R.; Rust, A.G.; Davey, N. (2009)Currently the best algorithms for predicting transcription factor binding sites in DNA sequences are severely limited in accuracy. There is good reason to believe that predictions from different classes of algorithms could ... -
An investigation into the performance and representation of a stochastic evolutionary neural tree
Butchart, K.; Davey, N.; Adams, R.G. (Springer Nature, 1997)The Stochastic Competitive Evolutionary Neural Tree (SCENT) is a new unsupervised neural net that dynamically evolves a representational structure in response to its training data. Uniquely SCENT requires no initial parameter ... -
Learning through experience: an emergent connectionist account of letter production behaviour
Richardson, F.M.; Davey, N.; Adams, R.G.; Done, D.J. (2006) -
Locally connected and small world associative memories in very large networks
Calcraft, L.; Adams, R.G.; Davey, N. (2006) -
Molecular self-organisation in a developmental model for the evolution of large-scale artificial neural networks
Bolouri, H.; Adams, R.G.; George, S.; Rust, A.G. (1998)We argue that molecular self-organisation during embryonic development allows evolution to perform highly nonlinear combinatorial optimisation. A structured approach to architectural optimisation of large-scale Artificial ... -
Non-Euclidean Norms and Data Normalisation
Doherty, K.; Adams, R.G.; Davey, N. (2004-04) -
Non-specific LTD at parallel fibre - Purkinje cell synapses in cerebellar cortex provides robustness against local spatial noise during pattern recognition
Safaryan, Karen; Maex, Reinoud; Adams, R.G.; Davey, N.; Steuber, Volker (2011)Poster presented at CNS 2011 -
Omni-directional motion: pedestrian shape classification using neural networks and active contour models
Tabb, Ken; George, S.; Davey, N.; Adams, R.G. (2001)This paper describes a hybrid vision system which, following initial user interaction, can detect and track objects in the visual field, and classify them as human and non-human. The system incorporates an active contour ... -
Optimal connection strategies in one- and two-dimensional associative memory models
Calcraft, L.; Adams, R.G.; Davey, N. (2007) -
Optimal noise in spiking neural networks for the detection of chemicals by simulated agents
Oros, N.; Steuber, Volker; Davey, N.; Cañamero, Lola; Adams, R.G. (MIT Press, 2008)We created a spiking neural controller for an agent that could use two different types of information encoding strategies depending on the level of chemical concentration present in the environment. The first goal of this ... -
Optimising a neural tree classifier using a genetic algorithm
Pensuwon, W.; Adams, R.G.; Davey, N. (2000)This paper documents experiments performed using a GA to optimise the parameters of a dynamic neural tree model. Two fitness functions were created from two selected clustering measures, and a population of genotypes, ...