Classification of electron sub-tomograms with neural networks and its application to template-matching

Classification of electron sub-tomograms is a challenging task, due the missing-wedge and the low signal-to-noise ratio of the data. Classification algorithms tend to classify data according to their orientation to the missing-wedge, rather than to the underlying signal. Here we use a neural network approach, called the Kernel Density Estimator Self-Organizing Map (KerDenSOM3D), which we have implemented in three-dimensions (3D), also having compensated for the missing-wedge, and we comprehensively compare it to other classification methods. For this purpose, we use various simulated macromolecules, as well as tomographically reconstructed in vitro GroEL and GroEL/GroES molecules. We show that the performance of this classification method is superior to previously used algorithms. Furthermore, we show how this algorithm can be used to provide an initial cross-validation of template-matching approaches. For the example of sub-tomogram classification extracted from cellular tomograms of Mycoplasma pneumonia and Spiroplasma melliferum cells, we show the bias of template-matching, and by using differing search and classification areas, we demonstrate how the bias can be significantly reduced.     

Global asymptotic stability of complex-valued neural networks with additive time-varying delays

In this paper, we extensively study the global asymptotic stability problem of complex-valued neural networks with leakage delay and additive time-varying delays. By constructing a suitable Lyapunov–Krasovskii functional and applying newly developed complex valued integral inequalities, sufficient conditions for the global asymptotic stability of proposed neural networks are established in the form of complex-valued linear matrix inequalities. This linear matrix inequalities are efficiently solved by using standard available numerical packages. Finally, three numerical examples are given to demonstrate the effectiveness of the theoretical results.     

Reverberations and control of neural networks

Summary The simulation of neural networks, such as the brain cortex, which have a diffuse and rather uniform structure quite unlike the simple block-structure of extant computers, leads naturally to the study of functions and principles which only in part fall within the scope of Automata Theory. Systems of decision equations must be studied with a view especially to obtaining practical means for the prevision and computation of diffuse reverberations of wanted general characteristics, with the exclusion of all others. This amounts to deriving constraints on the allowed variability of the couplings among elements during learning processes, failing which the behavior of the simulator would become uncontrollable for practical purposes. A simple mathematical treatment is presented, which essentially linearizes these problems by an appropriate use of matrix algebra and permits a straightforward study of the wanted conditions, as well as of the controlling elements which may have to be added to the network.This work has been performed in part at the Laboratoire de Physique Théorique et Hautes Energies, Faculté des Sciences de Paris.This work has been performed with the joint sponsorship of the U.S.A.F. and their European Office of Aerospace Research under contracts no. AF EOAR 66-25 and AF 33(615)-2786.We wish to express our sincere thanks to Dr. F. Lauria for many illuminated discussions; and to Prof. M. Lévy for his kind hospitality at the Laboratoire de physique Théorique, in Paris, where part of this research was made.     

OutbreakFlow: Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks and its application to the COVID-19 pandemics in Germany

Mathematical models in epidemiology are an indispensable tool to determine the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. However, reliably inferring the epidemical dynamics by connecting complex models to real data is still hard and requires either laborious manual parameter fitting or expensive optimization methods which have to be repeated from scratch for every application of a given model. In this work, we address this problem with a novel combination of epidemiological modeling with specialized neural networks. Our approach entails two computational phases: In an initial training phase, a mathematical model describing the epidemic is used as a coach for a neural network, which acquires global knowledge about the full range of possible disease dynamics. In the subsequent inference phase, the trained neural network processes the observed data of an actual outbreak and infers the parameters of the model in order to realistically reproduce the observed dynamics and reliably predict future progression. With its flexible framework, our simulation-based approach is applicable to a variety of epidemiological models. Moreover, since our method is fully Bayesian, it is designed to incorporate all available prior knowledge about plausible parameter values and returns complete joint posterior distributions over these parameters. Application of our method to the early Covid-19 outbreak phase in Germany demonstrates that we are able to obtain reliable probabilistic estimates for important disease characteristics, such as generation time, fraction of undetected infections, likelihood of transmission before symptom onset, and reporting delays using a very moderate amount of real-world observations.     

The uniqueness theorem for complex-valued neural networks with threshold parameters and the redundancy of the parameters

This paper will prove the uniqueness theorem for 3-layered complex-valued neural networks where the threshold parameters of the hidden neurons can take non-zeros. That is, if a 3-layered complex-valued neural network is irreducible, the 3-layered complex-valued neural network that approximates a given complex-valued function is uniquely determined up to a finite group on the transformations of the learnable parameters of the complex-valued neural network.     

人工神经网络在三化螟预测中的应用

本应用神经网络对闽北四代三化螟的发生情况进行了预测,三化螟的预报可视作高维空间的非线性分类问题。利用BP网络的反向传播算法．我们对三化螟种群发生趋势进行预测,并获得了满意的结果。     

Random simulation and confiners: Their application to neural networks

Random simulation of complex dynamical systems is generally used in order to obtain information about their asymptotic behaviour (i.e., when time or size of the system tends towards infinity). A fortunate and welcome circumstance in most of the systems studied by physicists, biologists, and economists is the existence of an invariant measure in the state space allowing determination of the frequency with which observation of asymptotic states is possible. Regions found between contour lines of the surface density of this invariant measure are called confiners. An example of such confiners is given for a formal neural network capable of learning. Finally, an application of this methodology is proposed in studying dependency of the network's invariant measure with regard to: 1) the mode of neurone updating (parallel or sequential), and 2) boundary conditions of the network (searching for phase transitions).     

Cardiovascular control with artificial neural networks

This paper describes the use of artificial neural networks to model cardiovascular autonomic control in a study of the hemodynamic changes associated with space flight. Cardiovascular system models were created including four parameters: heart rate, contractility, peripheral resistance, and venous tone. Artificial neural networks were then designed and trained. A technique known as backpropagation networking was used and the results of the application of this technique to heart rate control are presented and discussed.     

Prediction of signal peptides in protein sequences by neural networks

We present here a neural network-based method for detection of signal peptides (abbreviation used: SP) in proteins. The method is trained on sequences of known signal peptides extracted from the Swiss-Prot protein database and is able to work separately on prokaryotic and eukaryotic proteins. A query protein is dissected into overlapping short sequence fragments, and then each fragment is analyzed with respect to the probability of it being a signal peptide and containing a cleavage site. While the accuracy of the method is comparable to that of other existing prediction tools, it provides a significantly higher speed and portability. The accuracy of cleavage site prediction reaches 73% on heterogeneous source data that contains both prokaryotic and eukaryotic sequences while the accuracy of discrimination between signal peptides and non-signal peptides is above 93% for any source dataset. As a consequence, the method can be easily applied to genome-wide datasets. The software can be downloaded freely from http://rpsp.bioinfo.pl/RPSP.tar.gz.     

Phytoplankton community dynamics of two adjacent Dutch lakes in response to seasons and eutrophication control unravelled by non-supervised artificial neural networks

Long-term time-series of the eutrophic Dutch lakes Veluwemeer and Wolderwijd were subject to ordination and clustering by means of non-supervised artificial neural networks (ANN). A combination of bottom-up and top-down eutrophication control measures has been implemented in both lakes since 1979. Dividing time-series data from 1976 to 1993 into three distinctive management periods has facilitated a comparative analysis of the two lakes regarding both the seasonal and long-term dynamics in response to eutrophication control. Results of the study have demonstrated that non-supervised ANN are an alternative technique: (1) to elucidate causal relationships of complex ecological processes, and (2) to reveal long-term behaviours of ecosystems in response to different management approaches. It has been shown that external nutrient control combined with food web manipulation have turned both lakes from nitrogen to phosphorus limitation, and from blue-green algae to diatom and green algae dominance.     

Self-organized dynamics in plastic neural networks: bistability and coherence

 In this paper, we study the combined dynamics of the neural activity and the synaptic efficiency changes in a fully connected network of biologically realistic neurons with simple synaptic plasticity dynamics including both potentiation and depression. Using a mean-field of technique, we analyzed the equilibrium states of neural networks with dynamic synaptic connections and found a class of bistable networks. For this class of networks, one of the stable equilibrium states shows strong connectivity and coherent responses to external input. In the other stable equilibrium, the network is loosely connected and responds non coherently to external input. Transitions between the two states can be achieved by positively or negatively correlated external inputs. Such networks can therefore switch between their phases according to the statistical properties of the external input. Non-coherent input can only “rcad” the state of the network, while a correlated one can change its state. We speculate that this property, specific for plastic neural networks, can give a clue to understand fully unsupervised learning models. Received: 8 August 1999 / Accepted in revised form: 16 March 2000     

Homeostatic plasticity improves signal propagation in continuous-time recurrent neural networks

Continuous-time recurrent neural networks (CTRNNs) are potentially an excellent substrate for the generation of adaptive behaviour in artificial autonomous agents. However, node saturation effects in these networks can leave them insensitive to input and stop signals from propagating. Node saturation is related to the problems of hyper-excitation and quiescence in biological nervous systems, which are thought to be avoided through the existence of homeostatic plastic mechanisms. Analogous mechanisms are here implemented in a variety of CTRNN architectures and are shown to increase node sensitivity and improve signal propagation, with implications for robotics. These results lend support to the view that homeostatic plasticity may prevent quiescence and hyper-excitation in biological nervous systems.     

Spectrum of the nonstationary electromyographic signal modelled with integral pulse frequency modulation and its application to estimating neural drive information

The spectrum of nonstationary electromyographic signal (EMG) is investigated, from which the error for neural drive information estimation from nonstationary EMG is studied in terms of signal-to-noise ratio (SNR), in analytical, numerical simulation, and experimental work. The signal refers to the neural drive information embedded within the nonstationary EMG, and noise refers to other portions of EMG that induce error in the estimation. The analytical expressions for the SNRs of force-modulated EMG with both single and multiple motor units (MU) are derived based on a sinusoidal integral pulse frequency modulation (IPFM) model. It is shown that the previously developed SNR expressions for stationary (unmodulated) EMG are special cases of the formulas presented here. The SNR results obtained from numerical simulated EMG agree very well with the analytical result. Results from nonstationary (modulated) surface EMG obtained from seven subjects also match the analytical and simulation results reasonably well. The results obtained from this work establish an analytical framework in studying and estimating the neural drive information contained in the EMG in the context of anisotonic and isometric contractions. Through the analytical study, the effects of different physiological parameters are identified, thus providing theoretical guidelines for developing advanced signal processing methods for nonstationary EMG in applications such as prosthesis control.     

Global dynamics of a class of complex valued neural networks

In this paper activation dynamics of a complex valued neural network has been studied. Sufficient conditions for global exponential stability of a unique equilibrium are obtained. Our results show that in the serial mode of operation, the network converges to a stable state.     

Auto-validation of fluorescent primer extension genotyping assay using signal clustering and neural networks

Background

SNP genotyping typically incorporates a review step to ensure that the genotype calls for a particular SNP are correct. For high-throughput genotyping, such as that provided by the GenomeLab SNPstream^® instrument from Beckman Coulter, Inc., the manual review used for low-volume genotyping becomes a major bottleneck. The work reported here describes the application of a neural network to automate the review of results.

Results

We describe an approach to reviewing the quality of primer extension 2-color fluorescent reactions by clustering optical signals obtained from multiple samples and a single reaction set-up. The method evaluates the quality of the signal clusters from the genotyping results. We developed 64 scores to measure the geometry and position of the signal clusters. The expected signal distribution was represented by a distribution of a 64-component parametric vector obtained by training the two-layer neural network onto a set of 10,968 manually reviewed 2D plots containing the signal clusters.

Conclusion

The neural network approach described in this paper may be used with results from the GenomeLab SNPstream instrument for high-throughput SNP genotyping. The overall correlation with manual revision was 0.844. The approach can be applied to a quality review of results from other high-throughput fluorescent-based biochemical assays in a high-throughput mode.     

Dynamic memorization characteristics in neural networks with different neuronal dynamics

We introduce a stimulus-response scheme that supports plastic variation of synapse weights in neural networks, and analyze how memory formation evolves under external stimulation. In so doing, chaotic networks and stochastic networks that have very different dynamics are compared. Experimental results suggest that chaotic activity remarkably outperforms stochastic activity in stimulus-response memorization. This seems to be indicative of effectiveness of the chaos in dynamic learning by stimulus-response scheme oriented to natural learning.     

Nonlinear system identification and control based on modular neural networks

A new approach for nonlinear system identification and control based on modular neural networks (MNN) is proposed in this paper. The computational complexity of neural identification can be greatly reduced if the whole system is decomposed into several subsystems. This is obtained using a partitioning algorithm. Each local nonlinear model is associated with a nonlinear controller. These are also implemented by neural networks. The switching between the neural controllers is done by a dynamical switcher, also implemented by neural networks, that tracks the different operating points. The proposed multiple modelling and control strategy has been successfully tested on simulated laboratory scale liquid-level system.