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.

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.

Neuronal network dynamics during epileptogenesis in the medial temporal lobe

Epilepsy is one of the most common neurological disorders, a large fraction of which is resistant to pharmacotherapy. In this light, understanding the mechanisms of epilepsy and its intractable forms in particular could create new targets for pharmacotherapeutic intervention. The current project explores the dynamic changes in neuronal network function in the chronic temporal lobe epilepsy (TLE) in rat and human brain in vitro. I focused on the process of establishment of epilepsy (epileptogenesis) in the temporal lobe. Rhythmic behaviour of the hippocampal neuronal networks in healthy animals was explored using spontaneous oscillations in the gamma frequency band (SγO). The use of an improved brain slice preparation technique resulted in the natural occurence (in the absence of pharmacological stimulation) of rhythmic activity, which was then pharmacologically characterised and compared to other models of gamma oscillations (KA- and CCh-induced oscillations) using local field potential recording technique. The results showed that SγO differed from pharmacologically driven models, suggesting higher physiological relevance of SγO. Network activity was also explored in the medial entorhinal cortex (mEC), where spontaneous slow wave oscillations (SWO) were detected. To investigate the course of chronic TLE establishment, a refined Li-pilocarpine-based model of epilepsy (RISE) was developed. The model significantly reduced animal mortality and demonstrated reduced intensity, yet high morbidy with almost 70% mean success rate of developing spontaneous recurrent seizures. We used SγO to characterize changes in the hippocampal neuronal networks throughout the epileptogenesis. The results showed that the network remained largely intact, demonstrating the subtle nature of the RISE model. Despite this, a reduction in network activity was detected during the so-called latent (no seizure) period, which was hypothesized to occur due to network fragmentation and an abnormal function of kainate receptors (KAr). We therefore explored the function of KAr by challenging SγO with kainic acid (KA). The results demonstrated a remarkable decrease in KAr response during the latent period, suggesting KAr dysfunction or altered expression, which will be further investigated using a variety of electrophysiological and immunocytochemical methods. The entorhinal cortex, together with the hippocampus, is known to play an important role in the TLE. Considering this, we investigated neuronal network function of the mEC during epileptogenesis using SWO. The results demonstrated a striking difference in AMPAr function, with possible receptor upregulation or abnormal composition in the early development of epilepsy. Alterations in receptor function inevitably lead to changes in the network function, which may play an important role in the development of epilepsy. Preliminary investigations were made using slices of human brain tissue taken following surgery for intratctable epilepsy. Initial results showed that oscillogenesis could be induced in human brain slices and that such network activity was pharmacologically similar to that observed in rodent brain. Overall, our findings suggest that excitatory glutamatergic transmission is heavily involved in the process of epileptogenesis. Together with other types of receptors, KAr and AMPAr contribute to epilepsy establishment and may be the key to uncovering its mechanism.

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.

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.

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.

Beta frequency neuronal network activity in the primary motor cortex

In this study I investigated the mechanisms of neuronal network oscillatory activity in rat M1 using pharmacological manipulations and electrical stimulation protocols, employing the in vitro brain slice technique in rat and magnetoencephalography (MEG) in man. Co-application of kainic acid and carbachol generated in vitro beta oscillatory activity in all layers in M1. Analyses indicated that oscillations originated from deep layers and indicated significant involvement of GABAA receptors and gap junctions. A modulatory role of GABAB, NMDA, and dopamine receptors was also evident. Intracellular recordings from fast-spiking (FS) GABAergic inhibitory cells revealed phase-locked action potentials (APs) on every beta cycle. Glutamatergic excitatory regular-spiking (RS) and intrinsically-bursting (IB) cells both received phase locked inhibitory postsynaptic potentials, but did not fire APs on every cycle, suggesting the dynamic involvement of different pools of neurones in the overall population oscillations. Stimulation evoked activity at high frequency (HFS; 125Hz) evoked gamma oscillations and reduced ongoing beta activity. 20Hz stimulation promoted theta or gamma oscillations whilst 4Hz stimulation enhanced beta power at theta frequency. I also investigated the modulation of pathological slow wave (theta and beta) oscillatory activity using magnetoencephalography. Abnormal activity was suppressed by sub-sedative doses of GABAA receptor modulator zolpidem and the observed desynchronising effect correlated well with improved sensorimotor function. These studies indicate a fundamental role for inhibitory neuronal networks in the patterning beta activity and suggest that cortical HFS in PD re-patterns abnormally enhanced M1 network activity by modulating the activity of FS cells. Furthermore, pathological oscillation may be common to many neuropathologies and may be an important future therapeutic target.

MODELLING AND CONTROL OF ERSW PROCESSES BY NEURONAL NETWORK

A study on the use of artificial intelligence (AI) techniques for the modelling and subsequent control of an electric resistance spot welding process (ERSW) is presented. The ERSW process is characterized by the coupling of thermal, electrical, mechanical, and metallurgical phenomena. For this reason, early attempts to model it using computational methods established as the methods of finite differences, finite element, and finite volumes, ask for simplifications that lead the model obtained far from reality or very costly in terms of computational costs, to be used in a real-time control system. In this sense, the authors have developed an ERSW controller that uses fuzzy logic to adjust the energy transferred to the weld nugget. The proposed control strategies differ in the speed with which it reaches convergence. Moreover, their application for a quality control of spot weld through artificial neural networks (ANN) is discussed.

Dynamic artificial neural network for electricity market prices forecast

This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).

A numerical solver for a nonlinear Fokker-Planck equation representation of neuronal network dynamics

To describe the collective behavior of large ensembles of neurons in neuronal network, a kinetic theory description was developed in [13, 12], where a macroscopic representation of the network dynamics was directly derived from the microscopic dynamics of individual neurons, which are modeled by conductance-based, linear, integrate-and-fire point neurons. A diffusion approximation then led to a nonlinear Fokker-Planck equation for the probability density function of neuronal membrane potentials and synaptic conductances. In this work, we propose a deterministic numerical scheme for a Fokker-Planck model of an excitatory-only network. Our numerical solver allows us to obtain the time evolution of probability distribution functions, and thus, the evolution of all possible macroscopic quantities that are given by suitable moments of the probability density function. We show that this deterministic scheme is capable of capturing the bistability of stationary states observed in Monte Carlo simulations. Moreover, the transient behavior of the firing rates computed from the Fokker-Planck equation is analyzed in this bistable situation, where a bifurcation scenario, of asynchronous convergence towards stationary states, periodic synchronous solutions or damped oscillatory convergence towards stationary states, can be uncovered by increasing the strength of the excitatory coupling. Finally, the computation of moments of the probability distribution allows us to validate the applicability of a moment closure assumption used in [13] to further simplify the kinetic theory.

Identification of neuronal network properties from the spectral analysis of calcium imaging signals in neuronal cultures

Neuronal networks in vitro are prominent systems to study the development of connections in living neuronal networks and the interplay between connectivity, activity and function. These cultured networks show a rich spontaneous activity that evolves concurrently with the connectivity of the underlying network. In this work we monitor the development of neuronal cultures, and record their activity using calcium fluorescence imaging. We use spectral analysis to characterize global dynamical and structural traits of the neuronal cultures. We first observe that the power spectrum can be used as a signature of the state of the network, for instance when inhibition is active or silent, as well as a measure of the network's connectivity strength. Second, the power spectrum identifies prominent developmental changes in the network such as GABAA switch. And third, the analysis of the spatial distribution of the spectral density, in experiments with a controlled disintegration of the network through CNQX, an AMPA-glutamate receptor antagonist in excitatory neurons, reveals the existence of communities of strongly connected, highly active neurons that display synchronous oscillations. Our work illustrates the interest of spectral analysis for the study of in vitro networks, and its potential use as a network-state indicator, for instance to compare healthy and diseased neuronal networks.

Review of quantitative phase-digital holographic microscopy: promising novel imaging technique to resolve neuronal network activity and identify cellular biomarkers of psychiatric disorders.

Quantitative phase microscopy (QPM) has recently emerged as a new powerful quantitative imaging technique well suited to noninvasively explore a transparent specimen with a nanometric axial sensitivity. In this review, we expose the recent developments of quantitative phase-digital holographic microscopy (QP-DHM). Quantitative phase-digital holographic microscopy (QP-DHM) represents an important and efficient quantitative phase method to explore cell structure and dynamics. In a second part, the most relevant QPM applications in the field of cell biology are summarized. A particular emphasis is placed on the original biological information, which can be derived from the quantitative phase signal. In a third part, recent applications obtained, with QP-DHM in the field of cellular neuroscience, namely the possibility to optically resolve neuronal network activity and spine dynamics, are presented. Furthermore, potential applications of QPM related to psychiatry through the identification of new and original cell biomarkers that, when combined with a range of other biomarkers, could significantly contribute to the determination of high risk developmental trajectories for psychiatric disorders, are discussed.

Identification of neuronal network properties from the spectral analysis of calcium imaging signals in neuronal cultures

Neuronal networks in vitro are prominent systems to study the development of connections in living neuronal networks and the interplay between connectivity, activity and function. These cultured networks show a rich spontaneous activity that evolves concurrently with the connectivity of the underlying network. In this work we monitor the development of neuronal cultures, and record their activity using calcium fluorescence imaging. We use spectral analysis to characterize global dynamical and structural traits of the neuronal cultures. We first observe that the power spectrum can be used as a signature of the state of the network, for instance when inhibition is active or silent, as well as a measure of the network's connectivity strength. Second, the power spectrum identifies prominent developmental changes in the network such as GABAA switch. And third, the analysis of the spatial distribution of the spectral density, in experiments with a controlled disintegration of the network through CNQX, an AMPA-glutamate receptor antagonist in excitatory neurons, reveals the existence of communities of strongly connected, highly active neurons that display synchronous oscillations. Our work illustrates the interest of spectral analysis for the study of in vitro networks, and its potential use as a network-state indicator, for instance to compare healthy and diseased neuronal networks.

Architecture for Living Neuronal Network Control of a mobile robot

The intelligent controlling mechanism of a typical mobile robot is usually a computer system. Research is however now ongoing in which biological neural networks are being cultured and trained to act as the brain of an interactive real world robot – thereby either completely replacing or operating in a cooperative fashion with a computer system. Studying such neural systems can give a distinct insight into biological neural structures and therefore such research has immediate medical implications. The principal aims of the present research are to assess the computational and learning capacity of dissociated cultured neuronal networks with a view to advancing network level processing of artificial neural networks. This will be approached by the creation of an artificial hybrid system (animat) involving closed loop control of a mobile robot by a dissociated culture of rat neurons. This paper details the components of the overall animat closed loop system architecture and reports on the evaluation of the results from preliminary real-life and simulated robot experiments.

Input/output linearization using dynamic recurrent neural networks

This paper brings together two areas of research that have received considerable attention during the last years, namely feedback linearization and neural networks. A proposition that guarantees the Input/Output (I/O) linearization of nonlinear control affine systems with Dynamic Recurrent Neural Networks (DRNNs) is formulated and proved. The proposition and the linearization procedure are illustrated with the simulation of a single link manipulator.