- UHRA Home
- Browsing by Author
Browsing by Author "Hunt, S."
Now showing items 1-17 of 17
-
Applications of neural networks to telecommunications systems
Frank, R.; Davey, N.; Hunt, S. (ELITE Foundation, 1999)This paper gives an overview of a project involving the application of neural networks to Telecommunications Systems. Five application areas are discussed, including cloned software identification and the detection of ... -
Associative memory models with structured connectivity.
Turvey, S.P.; Hunt, S.; Frank, R.; Davey, N. (ACTA Press, 2003)High capacity associative memory models with dilute structured connectivity are trained using naturalistic bitmap patterns. The connectivity of the model is chosen to reflect the local spatial continuity of the data. The ... -
The capacity and attractor basins of associative memory models
Davey, N.; Hunt, S. (1999)The performance characteristics of five variants of the Hopfield network are examined. Two performance metrics are used: memory capacity, and a measure of the size of basins of attraction. We find that the posttraining ... -
A comparative analysis of high performance associative memory models.
Davey, N.; Hunt, S. (2000)Three variants of the Hopfield network are examined, each of which is trained using a different iterative approximation of the pseudo-inverse rule. All three variants are known to have significantly higher memory capacity ... -
Correcting Errors in Optical Data Transmission Using Neural Networks
Hunt, S.; Sun, Yi.; Shafarenko, A.; Adams, R.G.; Davey, N.; Slater, B.; Bhamber, R.; Boscolo, S.; Turitsyn, S.K. (2010)Optical data communication systems are prone to a variety of processes that modify the transmitted signal, and contribute errors in the determination of 1s from 0s. This is a difficult, and commercially important, problem ... -
Design and use of neural network applications in telecommunications
Frank, R.; Davey, N.; Hunt, S. (CRC Press, 2000)This chapter describes the use of neural networks in the analysis of software systems. The development of large software systems over long periods of time, and the software crisis that this has produced, provides a rich ... -
High capacity associative memory models - binary and bipolar representation
Davey, N.; Frank, R.; Hunt, S.; Adams, R.G.; Calcraft, L. (2004) -
High Capacity Recurrent Associative Memories
Davey, N.; Hunt, S.; Adams, R.G. (2004-12) -
High Performance Associative Memories and Structured Weight Dilution
Turvey, S.P.; Hunt, S.; Davey, N.; Frank, R. (Springer Nature, 2004)The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental ... -
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; ... -
Non-random weight dilution in high performance associative memories
Turvey, S.P.; Hunt, S.; Davey, N.; Frank, R. (2002) -
Optimal dilution and high capacity associative memories
Hunt, S.; Davey, N.; Frank, R. (2006) -
A simple yet accurate neural branch predictor.
Hunt, S.; Egan, C.; Shafarenko, A. (ACTA Press, 2003)In this paper, we examine the application of simple neural processing elements to the problem of dynamic branch prediction in high-performance processors. A single neural network model is considered: the Perceptron. We ... -
Structured connectivity in an associative memory model
Turvey, S.P.; Hunt, S.; Frank, R.; Adams, R.G.; Davey, N. (2004) -
Time Series Prediction and Neural Networks
Frank, R.; Davey, N.; Hunt, S. (2001) -
Time series prediction and neural networks
Davey, N.; Hunt, S.; Frank, R. (1999)Neural Network approaches to time series prediction are briefly discussed, and the need to specify an appropriately sized input window identified. Relevant theoretical results from dynamic systems theory are introduced, ... -
Using Simple Neural Networks to Correct Errors in Optical Data Transmission.
Hunt, S.; Sun, Yi; Shafarenko, A.; Davey, N.; Boscolo, S.; Turitsyn, S.K. (De Montfort University, 2008)We have demonstrated the applicability of neural-network-based systems to the problem of reducing the effects of signal distortion, and shown that such a system has the potential to reduce the bit-error-rate in the ...