Dynamical system parameter identification using deep recurrent cell networks

Neural Computing and Applications - In this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear...     

Effects of spike timing on winner-take-all competition in model cortical circuits

Synaptic interactions in cortical circuits involve strong recurrent excitation between nearby neurons and lateral inhibition that is more widely spread. This architecture is commonly thought to promote a winner-take-all competition, in which a small fraction of neuronal responses is selected for further processing. Here I report that such a competition is remarkably sensitive to the timing of neuronal action potentials. This is shown using simulations of model neurons and synaptic connections representing a patch of cortical tissue. In the simulations, uncorrelated discharge among neuronal units results in patterns of response dominance and suppression, that is, in a winner-take-all competition. Synchronization of firing, however, prevents such competition. These results demonstrate a novel property of recurrent cortical-like circuits, suggesting that the temporal patterning of cortical activity may play an important part in selection among stimuli competing for the control of attention and motor action.     

Multiple constraints to compute optical flow

The computation of the optical flow field from an image sequence requires the definition of constraints on the temporal change of image features. In this paper, we consider the implications of using multiple constraints in the computational schema. In the first step, it is shown that differential constraints correspond to an implicit feature tracking. Therefore, the best results (either in terms of measurement accuracy, and speed in the computation) are obtained by selecting and applying the constraints which are best “tuned” to the particular image feature under consideration. Considering also multiple image points not only allows us to obtain a (locally) better estimate of the velocity field, but also to detect erroneous measurements due to discontinuities in the velocity field. Moreover, by hypothesizing a constant acceleration motion model, also the derivatives of the optical flow are computed. Several experiments are presented from real image sequences     

Robust reinforcement learning control using integral quadratic constraints for recurrent neural networks.

The applicability of machine learning techniques for feedback control systems is limited by a lack of stability guarantees. Robust control theory offers a framework for analyzing the stability of feedback control loops, but for the integral quadratic constraint (IQC) framework used here, all components are required to be represented as linear, time-invariant systems plus uncertainties with, for IQCs used here, bounded gain. In this paper, the stability of a control loop including a recurrent neural network (NN) is analyzed by replacing the nonlinear and time-varying components of the NN with IQCs on their gain. As a result, a range of the NN's weights is found within which stability is guaranteed. An algorithm is demonstrated for training the recurrent NN using reinforcement learning and guaranteeing stability while learning.     

Information recall using relative spike timing in a spiking neural network

We present a neural network that is capable of completing and correcting a spiking pattern given only a partial, noisy version. It operates in continuous time and represents information using the relative timing of individual spikes. The network is capable of correcting and recalling multiple patterns simultaneously. We analyze the network's performance in terms of information recall. We explore two measures of the capacity of the network: one that values the accurate recall of individual spike times and another that values only the presence or absence of complete patterns. Both measures of information are found to scale linearly in both the number of neurons and the period of the patterns, suggesting these are natural measures of network information. We show a smooth transition from encodings that provide precise spike times to flexible encodings that can encode many scenes. This makes it plausible that many diverse tasks could be learned with such an encoding.     

Analog-digital simulations of full conductance-based networks of spiking neurons with spike timing dependent plasticity

We introduce and test a system for simulating networks of conductance-based neuron models using analog circuits. At the single-cell level, we use custom-designed analog circuits (ASICs) that simulate two types of spiking neurons based on Hodgkin-Huxley like dynamics: "regular spiking" excitatory neurons with spike-frequency adaptation, and "fast spiking" inhibitory neurons. Synaptic interactions are mediated by conductance-based synaptic currents described by kinetic models. Connectivity and plasticity rules are implemented digitally through a real time interface between a computer and a PCI board containing the ASICs. We show a prototype system of a few neurons interconnected with synapses undergoing spike-timing dependent plasticity (STDP), and compare this system with numerical simulations. We use this system to evaluate the effect of parameter dispersion on the behavior of small circuits of neurons. It is shown that, although the exact spike timings are not precisely emulated by the ASIC neurons, the behavior of small networks with STDP matches that of numerical simulations. Thus, this mixed analog-digital architecture provides a valuable tool for real-time simulations of networks of neurons with STDP. They should be useful for any real-time application, such as hybrid systems interfacing network models with biological neurons.     

Acoustic-to-phonetic mapping using recurrent neural networks

This paper describes the application of artificial neural networks to acoustic-to-phonetic mapping. The experiments described are typical of problems in speech recognition in which the temporal nature of the input sequence is critical. The specific task considered is that of mapping formant contours to the corresponding CVC' syllable. We performed experiments on formant data extracted from the acoustic speech signal spoken at two different tempos (slow and normal) using networks based on the Elman simple recurrent network model. Our results show that the Elman networks used in these experiments were successful in performing the acoustic-to-phonetic mapping from formant contours. Consequently, we demonstrate that relatively simple networks, readily trained using standard backpropagation techniques, are capable of initial and final consonant discrimination and vowel identification for variable speech rates     

Financial volatility trading using recurrent neural networks

We simulate daily trading of straddles on financial indexes. The straddles are traded based on predictions of daily volatility differences in the indexes. The main predictive models studied are recurrent neural nets (RNN). Such applications have often been studied in isolation. However, due to the special character of daily financial time-series, it is difficult to make full use of RNN representational power. Recurrent networks either tend to overestimate noisy data, or behave like finite-memory sources with shallow memory; they hardly beat classical fixed-order Markov models. To overcome data nonstationarity, we use a special technique that combines sophisticated models fitted on a larger data set, with a fixed set of simple-minded symbolic predictors using only recent inputs. Finally, we compare our predictors with the GARCH family of econometric models designed to capture time-dependent volatility structure in financial returns. GARCH models have been used to trade volatility. Experimental results show that while GARCH models cannot generate any significantly positive profit, by careful use of recurrent networks or Markov models, the market makers can generate a statistically significant excess profit, but then there is no reason to prefer RNN over much more simple and straightforward Markov models. We argue that any report containing RNN results on financial tasks should be accompanied by results achieved by simple finite-memory sources combined with simple techniques to fight nonstationarity in the data.     

Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions

We establish two conditions that ensure the nondivergence of additive recurrent networks with unsaturating piecewise linear transfer functions, also called linear threshold or semilinear transfer functions. As Hahnloser, Sarpeshkar, Mahowald, Douglas, and Seung (2000) showed, networks of this type can be efficiently built in silicon and exhibit the coexistence of digital selection and analog amplification in a single circuit. To obtain this behavior, the network must be multistable and nondivergent, and our conditions allow determining the regimes where this can be achieved with maximal recurrent amplification. The first condition can be applied to nonsymmetric networks and has a simple interpretation of requiring that the strength of local inhibition match the sum over excitatory weights converging onto a neuron. The second condition is restricted to symmetric networks, but can also take into account the stabilizing effect of nonlocal inhibitory interactions. We demonstrate the application of the conditions on a simple example and the orientation-selectivity model of Ben-Yishai, Lev Bar-Or, and Sompolinsky (1995). We show that the conditions can be used to identify in their model regions of maximal orientation-selective amplification and symmetry breaking.     

Selecting and using views to compute aggregate queries

We consider a workload of aggregate queries and investigate the problem of selecting materialized views that (1) provide equivalent rewritings for all the queries, and (2) are optimal, in that the cost of evaluating the query workload is minimized. We consider conjunctive views and rewritings, with or without aggregation; in each rewriting, only one view contributes to computing the aggregated query output. We look at query rewriting using existing views and at view selection. In the query-rewriting problem, we give sufficient and necessary conditions for a rewriting to exist. For view selection, we prove complexity results. Finally, we give algorithms for obtaining rewritings and selecting views.     

Training recurrent neural networks using a hybrid algorithm

This paper proposes a new hybrid approach for recurrent neural networks (RNN). The basic idea of this approach is to train an input layer by unsupervised learning and an output layer by supervised learning. In this method, the Kohonen algorithm is used for unsupervised learning, and dynamic gradient descent method is used for supervised learning. The performances of the proposed algorithm are compared with backpropagation through time (BPTT) on three benchmark problems. Simulation results show that the performances of the new proposed algorithm exceed the standard backpropagation through time in the reduction of the total number of iterations and in the learning time required in the training process.     

Uncertainty-aware soft sensor using Bayesian recurrent neural networks

Data-driven soft sensors have been widely used to measure key variables for industrial processes. Soft sensors using deep learning models have attracted considerable attention and shown superior predictive performance. However, if a soft sensor encounters an unexpected situation in inferring data or if noisy input data is used, the estimated value derived by a standard soft sensor using deep learning may at best be untrustworthy. This problem can be mitigated by expressing a degree of uncertainty about the trustworthiness of the estimated value produced by the soft sensor. To address this issue of uncertainty, we propose using an uncertainty-aware soft sensor that uses Bayesian recurrent neural networks (RNNs). The proposed soft sensor uses a RNN model as a backbone and is then trained using Bayesian techniques. The experimental results demonstrated that such an uncertainty-aware soft sensor increases the reliability of predictive uncertainty. In comparisons with a standard soft sensor, it shows a capability to use uncertainties for interval prediction without compromising predictive performance.     

Signal parameter tracking algorithms using hybrid recurrent networks

Several explicit algorithms for tracking the parameters of second order models have been derived by the authors based on information available from the system time trajectory. In this paper the problem is recast in terms of recurrent integral-hybrid networks used in a hierarchical formation for both the reduced order model and to estimate the derivatives for parameter tracking. We relax the constant parameter condition by assuming linear time variation, the additional information is extracted from the system output trajectory by obtaining higher time derivatives which result in explicit functions to track the parameters online.     

Forecasting foreign exchange rates using recurrent neural networks

This article proposes the use of recurrent neural networks in order to forecast foreign exchange rates. Artificial neural networks have proven to be efficient and profitable in fore casting financial time series. In particular, recurrent networks in which activity patterns pass through the network more than once before they generate an output pattern can learn ex tremely complex temporal sequences. Three recurrent architectures are compared in terms of prediction accuracy of futures forecast for Deutsche mark currency. A trading strategy is then devised and optimized. The profitability of the trading strategy taking into account trans action costs is shown for the different architectures. The methods described here which have obtained promising results in real time trading are applicable to other markets.     

Efficient algorithms to compute Hankel transforms using wavelets

The aim of the paper is to propose two efficient algorithms for the numerical evaluation of Hankel transform of order ν, ν>−1 using Legendre and rationalized Haar (RH) wavelets. The philosophy behind the algorithms is to replace the part xf(x) of the integrand by its wavelet decomposition obtained by using Legendre wavelets for the first algorithm and RH wavelets for the second one, thus representing Fν(y) as a Fourier-Bessel series with coefficients depending strongly on the input function xf(x) in both the cases. Numerical evaluations of test functions with known analytical Hankel transforms illustrate the proposed algorithms.     

On satisfying timing constraints in hard-real-time systems

The authors explain why pre-run-time scheduling is essential if one wishes to guarantee that timing constraints will be satisfied in a large complex hard-real-time system. They examine some of the major concerns in pre-run-time scheduling and consider what formulations of mathematical scheduling problems can be used to address those concerns. This work provides a guide to the available algorithms     

A new general method to compute virtual channels occupancy probabilities in wormhole networks

Virtual channels have been proposed to develop deadlock free routing algorithms and to overcome the performance degradation due to chains of blocked messages in wormhole switched networks. Hence, capturing the effect of virtual channels has always been an important issue in developing analytical performance models for these interconnection networks. Almost all previous models relayed on a method proposed by Dally to compute the probability of the number of busy virtual channels per physical channel. Dally's method is based on a Markov chain and after extensive investigation our results reveal that its accuracy degrades as traffic increases. In this study we propose and validate a new general method to compute this probability. The new general method is based on an M/G/1 queue and it exhibits a good degree of accuracy at different traffic conditions. We further showed that Dally's method can be deduced as a special case of the general method. Predictions from both, Dally's method and the new general method are validated against results obtained from an event-driven simulator that mimics the behaviour of wormhole-switch networks.     

采用权函数计时的无线传感器网络分簇算法

为进一步降低无线传感器网络的能耗,提出了一种采用权函数计时的无线传感网络分簇路由算法。算法构建了节点聚合度与剩余能量之间的权函数,并以此为标准进行计时分簇,根据各节点权函数值与计时时长的差异来选举合理的簇头。在该路由算法下,周期性的分簇过程中节点不需交换各自的节点聚合度信息,降低了网络通信量,进而降低了网络能耗。仿真实验结果表明该算法成簇收敛性好,成簇规模稳定,能有效延长网络生存周期。     

State estimation in MIMO nonlinear systems subject to unknown deadzones using recurrent neural networks

This paper deals with the problem of state observation by means of a continuous-time recurrent neural network for a broad class of MIMO unknown nonlinear systems subject to unknown but bounded disturbances and with an unknown deadzone at each input. With respect to previous works, the main contribution of this study is twofold. On the one hand, the need of a matrix Riccati equation is conveniently avoided; in this way, the design process is considerably simplified. On the other hand, a faster convergence is carried out. Specifically, the exponential convergence of Euclidean norm of the observation error to a bounded zone is guaranteed. Likewise, the weights are shown to be bounded. The main tool to prove these results is Lyapunov-like analysis. A numerical example confirms the feasibility of our proposal.     

Effective hate-speech detection in Twitter data using recurrent neural networks

This paper addresses the important problem of discerning hateful content in social media. We propose a detection scheme that is an ensemble of Recurrent Neural Network (RNN) classifiers, and it incorporates various features associated with user-related information, such as the users’ tendency towards racism or sexism. This data is fed as input to the above classifiers along with the word frequency vectors derived from the textual content. We evaluate our approach on a publicly available corpus of 16k tweets, and the results demonstrate its effectiveness in comparison to existing state-of-the-art solutions. More specifically, our scheme can successfully distinguish racism and sexism messages from normal text, and achieve higher classification quality than current state-of-the-art algorithms.