The relative order and inverses of recurrent networks

Differential geometry is used to investigate the structure of neural-network-based control systems. The key aspect is relative order—an invariant property of dynamic systems. Finite relative order allows the specification of a minimal architecture for a recurrent network. Any system with finite relative order has a left inverse. It is shown that a recurrent network with finite relative order has a local inverse that is also a recurrent network with the same weights. The results have implications for the use of recurrent networks in the inverse-model-based control of nonlinear systems.

Dynamic recurrent neural network for system identification and control

A dynamic recurrent neural network (DRNN) that can be viewed as a generalisation of the Hopfield neural network is proposed to identify and control a class of control affine systems. In this approach, the identified network is used in the context of the differential geometric control to synthesise a state feedback that cancels the nonlinear terms of the plant yielding a linear plant which can then be controlled using a standard PID controller.

Stable receding horizon control based on recurrent networks

The last decade has seen the re-emergence of artificial neural networks as an alternative to traditional modelling techniques for the control of nonlinear systems. Numerous control schemes have been proposed and have been shown to work in simulations. However, very few analyses have been made of the working of these networks. The authors show that a receding horizon control strategy based on a class of recurrent networks can stabilise nonlinear systems.

Approximation of non-autonomous dynamic systems by continuous time recurrent neural networks

This work provides a framework for the approximation of a dynamic system of the form x˙=f(x)+g(x)u by dynamic recurrent neural network. This extends previous work in which approximate realisation of autonomous dynamic systems was proven. Given certain conditions, the first p output neural units of a dynamic n-dimensional neural model approximate at a desired proximity a p-dimensional dynamic system with n>p. The neural architecture studied is then successfully implemented in a nonlinear multivariable system identification case study.

Inverting recurrent neural networks for internal model control of nonlinear systems

In this paper, we show how a set of recently derived theoretical results for recurrent neural networks can be applied to the production of an internal model control system for a nonlinear plant. The results include determination of the relative order of a recurrent neural network and invertibility of such a network. A closed loop controller is produced without the need to retrain the neural network plant model. Stability of the closed-loop controller is also demonstrated.

A practical approach for training dynamic recurrent neural networks: use of Apriori information

Presents a technique for incorporating a priori knowledge from a state space system into a neural network training algorithm. The training algorithm considered is that of chemotaxis and the networks being trained are recurrent neural networks. Incorporation of the a priori knowledge ensures that the resultant network has behaviour similar to the system which it is modelling.

Internal model control of nonlinear systems through the inversion of recurrent neural networks

Recurrent neural networks can be used for both the identification and control of nonlinear systems. This paper takes a previously derived set of theoretical results about recurrent neural networks and applies them to the task of providing internal model control for a nonlinear plant. Using the theoretical results, we show how an inverse controller can be produced from a neural network model of the plant, without the need to train an additional network to perform the inverse control.

Dynamic input/output linearization using recurrent neural networks

A dynamic recurrent neural network (DRNN) is used to input/output linearize a control affine system in the globally linearizing control (GLC) structure. The network is trained as a part of a closed loop that involves a PI controller, the goal is to use the network, as a dynamic feedback, to cancel the nonlinear terms of the plant. The stability of the configuration is guarantee if the network and the plant are asymptotically stable and the linearizing input is bounded.

Identification of nonlinear systems with a dynamic recurrent neural network

Two approaches are presented to calculate the weights for a Dynamic Recurrent Neural Network (DRNN) in order to identify the input-output dynamics of a class of nonlinear systems. The number of states of the identified network is constrained to be the same as the number of states of the plant.

Relative order defines a topology for recurrent networks

This paper uses techniques from control theory in the analysis of trained recurrent neural networks. Differential geometry is used as a framework, which allows the concept of relative order to be applied to neural networks. Any system possessing finite relative order has a left-inverse. Any recurrent network with finite relative order also has an inverse, which is shown to be a recurrent network.

Computing journey start times with recurrent traffic conditions

n this study, the authors discuss the effective usage of technology to solve the problem of deciding on journey start times for recurrent traffic conditions. The developed algorithm guides the vehicles to travel on more reliable routes that are not easily prone to congestion or travel delays, ensures that the start time is as late as possible to avoid the traveller waiting too long at their destination and attempts to minimise the travel time. Experiments show that in order to be more certain of reaching their destination on time, a traveller has to leave early and correspondingly arrive early, resulting in a large waiting time. The application developed here asks the user to set this certainty factor as per the task in hand, and computes the best start time and route.

Coupling between gamma-band power and cerebral blood volume during recurrent acute neocortical seizures

Characterization of neural and hemodynamic biomarkers of epileptic activity that can be measured using noninvasive techniques is fundamental to the accurate identification of the epileptogenic zone (EZ) in the clinical setting. Recently, oscillations at gamma-band frequencies and above (N30 Hz) have been suggested to provide valuable localizing information of the EZ and track cortical activation associated with epileptogenic processes. Although a tight coupling between gamma-band activity and hemodynamic-based signals has been consistently demonstrated in non-pathological conditions, very little is known about whether such a relationship is maintained in epilepsy and the laminar etiology of these signals. Confirmation of this relationship may elucidate the underpinnings of perfusion-based signals in epilepsy and the potential value of localizing the EZ using hemodynamic correlates of pathological rhythms. Here, we use concurrent multi-depth electrophysiology and 2- dimensional optical imaging spectroscopy to examine the coupling between multi-band neural activity and cerebral blood volume (CBV) during recurrent acute focal neocortical seizures in the urethane-anesthetized rat. We show a powerful correlation between gamma-band power (25–90 Hz) and CBV across cortical laminae, in particular layer 5, and a close association between gamma measures and multi-unit activity (MUA). Our findings provide insights into the laminar electrophysiological basis of perfusion-based imaging signals in the epileptic state and may have implications for further research using non-invasive multi-modal techniques to localize epileptogenic tissue

Recurrent sores by ill-fitting dentures and intra-oral squamous cell carcinoma in smokers

Objectives: To examine whether denture use and recurrent sores caused by ill-fitting dentures are associated with intra-oral squamous cell carcinoma (IO-SCC) in individuals exposed to tobacco. Methods: We conducted a hospital-based case-control study. The study population comprised 124 patients with IO-SCC and the same number of controls (individually paired according to gender and age) recruited from outpatient units of the same hospital. Conditional logistic regression analysis assessed the effect of denture use and recurrent oral sores by ill-fitting dentures, adjusted by covariates on the lifetime exposure to alcohol and tobacco, socioeconomic standings, and dietary patterns. Results: The use of dentures showed no association with IO-SCC [adjusted odds ratio (OR) 1.40, 95 percent confidence interval 0.51-3.87, P = 0.513] in an assessment controlled by socioeconomic position, lifetime exposure to alcohol and tobacco, and dietary patterns. However, the report of recurrent sores caused by ill-fitting dentures showed significant association with the disease (adjusted OR 4.58, 95 percent confidence interval 1.52-13.76, P = 0.007). Conclusions: The association between recurrent oral sores caused by ill-fitting dentures and squamous cell carcinoma of the mouth in smokers is in agreement with the hypothesis that the chronic physical irritation of oral mucosa contributes to the topical carcinogenic effect of tobacco, which must be taken into careful consideration in the planning of dental services for adults and the elderly.