Development of low entropy coding in a recurrent network.

In this paper we present an unsupervised neural network which exhibits competition between units via inhibitory feedback. The operation is such as to minimize reconstruction error, both for individual patterns, and over the entire training set. A key difference from networks which perform principal components analysis, or one of its variants, is the ability to converge to non-orthogonal weight values. We discuss the network's operation in relation to the twin goals of maximizing information transfer and minimizing code entropy, and show how the assignment of prior probabilities to network outputs can help to reduce entropy. We present results from two binary coding problems, and from experiments with image coding.

Linear quadratic game and non-cooperative predictive methods for potential application to modelling driver-AFS interactive steering control

This paper is concerned with the modelling of strategic interactions between the human driver and the vehicle active front steering (AFS) controller in a path-following task where the two controllers hold different target paths. The work is aimed at extending the use of mathematical models in representing driver steering behaviour in complicated driving situations. Two game theoretic approaches, namely linear quadratic game and non-cooperative model predictive control (non-cooperative MPC), are used for developing the driver-AFS interactive steering control model. For each approach, the open-loop Nash steering control solution is derived; the influences of the path-following weights, preview and control horizons, driver time delay and arm neuromuscular system (NMS) dynamics are investigated, and the CPU time consumed is recorded. It is found that the two approaches give identical time histories as well as control gains, while the non-cooperative MPC method uses much less CPU time. Specifically, it is observed that the introduction of weight on the integral of vehicle lateral displacement error helps to eliminate the steady-state path-following error; the increase in preview horizon and NMS natural frequency and the decline in time delay and NMS damping ratio improve the path-following accuracy. © 2013 Copyright Taylor and Francis Group, LLC.

Masonry response to tunnelling: a sensitivity study on the effect of cracking and building weight

Predicting damage to masonry structures due to tunnelling-induced ground movements remains a challenge for practising design engineers. Useful simplified procedures exist, but more detailed analysis has the potential to improve these procedures. This paper considers the use of finite element modelling, including non-linear constitutive laws for the soil and the structure, to simulate damage to a simple masonry structure subjected to tunnelling in sand. The numerical model is validated through comparison with the results of a series of centrifuge tests and used to perform a sensitivity study on the effect of building weight and masonry damage on the structural response. Results show a direct correlation between the weight of the structure, normalised to the relative stiffness between the structure and the soil, and the modification of the settlement profile. By including a cracking model for the masonry, the reduction in structural stiffness caused by progressive masonry damage is also proven to affect the building deflection.