The impact of architecture on the performance of artificial neural networks

A number of researchers have investigated the impact of network architecture on the performance of artificial neural networks. Particular attention has been paid to the impact on the performance of the multi-layer perceptron of architectural issues, and the use of various strategies to attain an optimal network structure. However, there are still perceived limitations with the multi-layer perceptron and networks that employ a different architecture to the multi-layer perceptron have gained in popularity in recent years, particularly, networks that implement a more localised solution, where the solution in one area of the problem space does not impact, or has a minimal impact, on other areas of the space. In this study, we discuss the major architectural issues affecting the performance of a multi-layer perceptron, before moving on to examine in detail the performance of a new localised network, namely the bumptree. The work presented here examines the impact on the performance of artificial neural networks of employing alternative networks to the long established multi-layer perceptron. In particular, networks that impose a solution where the impact of each parameter in the final network architecture has a localised impact on the problem space being modelled are examined. The alternatives examined are the radial basis function and bumptree neural networks, and the impact of architectural issues on the performance of these networks is examined. Particular attention is paid to the bumptree, with new techniques for both developing the bumptree structure and employing this structure to classify patterns being examined.

Neural network enhanced self tuning adaptive control application for non-linear control of dynamic systems

The main theme of research of this project concerns the study of neutral networks to control uncertain and non-linear control systems. This involves the control of continuous time, discrete time, hybrid and stochastic systems with input, state or output constraints by ensuring good performances. A great part of this project is devoted to the opening of frontiers between several mathematical and engineering approaches in order to tackle complex but very common non-linear control problems. The objectives are: 1. Design and develop procedures for neutral network enhanced self-tuning adaptive non-linear control systems; 2. To design, as a general procedure, neural network generalised minimum variance self-tuning controller for non-linear dynamic plants (Integration of neural network mapping with generalised minimum variance self-tuning controller strategies); 3. To develop a software package to evaluate control system performances using Matlab, Simulink and Neural Network toolbox. An adaptive control algorithm utilising a recurrent network as a model of a partial unknown non-linear plant with unmeasurable state is proposed. Appropriately, it appears that structured recurrent neural networks can provide conveniently parameterised dynamic models for many non-linear systems for use in adaptive control. Properties of static neural networks, which enabled successful design of stable adaptive control in the state feedback case, are also identified. A survey of the existing results is presented which puts them in a systematic framework showing their relation to classical self-tuning adaptive control application of neural control to a SISO/MIMO control. Simulation results demonstrate that the self-tuning design methods may be practically applicable to a reasonably large class of unknown linear and non-linear dynamic control systems.

Growing Neural Networks Using Nonconventional Activation Functions

In the paper, an ontogenic artificial neural network (ANNs) is proposed. The network uses orthogonal activation functions that allow significant reducing of computational complexity. Another advantage is numerical stability, because the system of activation functions is linearly independent by definition. A learning procedure for proposed ANN with guaranteed convergence to the global minimum of error function in the parameter space is developed. An algorithm for structure network structure adaptation is proposed. The algorithm allows adding or deleting a node in real-time without retraining of the network. Simulation results confirm the efficiency of the proposed approach.

Neural Network Based Approach for Developing the Enterprise Strategy

Modern enterprises work in highly dynamic environment. Thus, the developing of company strategy is of crucial importance. It determines the surviving of the enterprise and its evolution. Adapting the desired management goal in accordance with the environment changes is a complex problem. In the present paper, an approach for solving this problem is suggested. It is based on predictive control philosophy. The enterprise is modelled as a cybernetic system and the future plant response is predicted by a neural network model. The predictions are passed to an optimization routine, which attempts to minimize the quadratic performance criterion.

Training a Linear Neural Network with a Stable LSP Solution for Jamming Cancellation

Two jamming cancellation algorithms are developed based on a stable solution of least squares problem (LSP) provided by regularization. They are based on filtered singular value decomposition (SVD) and modifications of the Greville formula. Both algorithms allow an efficient hardware implementation. Testing results on artificial data modeling difficult real-world situations are also provided.

Intellect Sensing of Neural Network that Trained to Classify Complex Signals

An experimental comparison of information features used by neural network is performed. The sensing method was used. Suboptimal classifier agreeable to the gaussian model of the training data was used as a probe. Neural nets with architectures of perceptron and feedforward net with one hidden layer were used. The experiments were carried out with spatial ultrasonic data, which are used for car’s passenger safety system neural controller learning. In this paper we show that a neural network doesn’t fully make use of gaussian components, which are first two moment coefficients of probability distribution. On the contrary, the network can find more complicated regularities inside data vectors and thus shows better results than suboptimal classifier. The parallel connection of suboptimal classifier improves work of modular neural network whereas its connection to the network input improves the specialization effect during training.

Artificial neural networks for surface roughness prediction when face milling Al 7075-T7351

In this work, different artificial neural networks (ANN) are developed for the prediction of surface roughness (R a) values in Al alloy 7075-T7351 after face milling machining process. The radial base (RBNN), feed forward (FFNN), and generalized regression (GRNN) networks were selected, and the data used for training these networks were derived from experiments conducted using a high-speed milling machine. The Taguchi design of experiment was applied to reduce the time and cost of the experiments. From this study, the performance of each ANN used in this research was measured with the mean square error percentage and it was observed that FFNN achieved the best results. Also the Pearson correlation coefficient was calculated to analyze the correlation between the five inputs (cutting speed, feed per tooth, axial depth of cut, chip°s width, and chip°s thickness) selected for the network with the selected output (surface roughness). Results showed a strong correlation between the chip thickness and the surface roughness followed by the cutting speed. © ASM International.

A new unsupervised convolutional neural network model for Chinese scene text detection

As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-Train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-Trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.

A research platform for artificial neural networks with applications in pediatric epilepsy

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of unique features has been implemented in NeuralStudio, such as ROC analysis, cross-validation, network averaging, topology optimization, and optimization of the activation function’s slopes. It also included a Support Vector Machines module for comparison purposes. Once the tool was fully developed, it was applied to two studies in brain research. In the first study, the goal was to create and train an ANN to detect epileptic seizures from subdural EEG. This analysis involved extracting features from the spectral power in the gamma frequencies. In the second application, a unique method was devised to link EEG recordings to epileptic and nonepileptic subjects. The contribution of this method consisted of developing a descriptor matrix that can be used to represent any EEG file regarding its duration and the number of electrodes. The first study showed that the inter-electrode mean of the spectral power in the gamma frequencies and its duration above a specific threshold performs better than the other frequencies in seizure detection, exhibiting an accuracy of 95.90%, a sensitivity of 92.59%, and a specificity of 96.84%. The second study yielded that Hjorth’s parameter activity is sufficient to accurately relate EEG to epileptic and non-epileptic subjects. After testing, accuracy, sensitivity and specificity of the classifier were all above 0.9667. Statistical tests measured the superiority of activity at over 99.99 % certainty. It was demonstrated that (1) the spectral power in the gamma frequencies is highly effective in locating seizures from EEG and (2) activity can be used to link EEG recordings to epileptic and non-epileptic subjects. These two studies required high computational load and could be addressed thanks to NeuralStudio. From a medical perspective, both methods proved the merits of NeuralStudio in brain research applications. For its outstanding features, NeuralStudio has been recently awarded a patent (US patent No. 7502763).

A Research Platform for Artificial Neural Networks with Applications in Pediatric Epilepsy

This dissertation established a state-of-the-art programming tool for designing and training artificial neural networks (ANNs) and showed its applicability to brain research. The developed tool, called NeuralStudio, allows users without programming skills to conduct studies based on ANNs in a powerful and very user friendly interface. A series of unique features has been implemented in NeuralStudio, such as ROC analysis, cross-validation, network averaging, topology optimization, and optimization of the activation function’s slopes. It also included a Support Vector Machines module for comparison purposes. Once the tool was fully developed, it was applied to two studies in brain research. In the first study, the goal was to create and train an ANN to detect epileptic seizures from subdural EEG. This analysis involved extracting features from the spectral power in the gamma frequencies. In the second application, a unique method was devised to link EEG recordings to epileptic and non-epileptic subjects. The contribution of this method consisted of developing a descriptor matrix that can be used to represent any EEG file regarding its duration and the number of electrodes. The first study showed that the inter-electrode mean of the spectral power in the gamma frequencies and its duration above a specific threshold performs better than the other frequencies in seizure detection, exhibiting an accuracy of 95.90%, a sensitivity of 92.59%, and a specificity of 96.84%. The second study yielded that Hjorth’s parameter activity is sufficient to accurately relate EEG to epileptic and non-epileptic subjects. After testing, accuracy, sensitivity and specificity of the classifier were all above 0.9667. Statistical tests measured the superiority of activity at over 99.99 % certainty. It was demonstrated that 1) the spectral power in the gamma frequencies is highly effective in locating seizures from EEG and 2) activity can be used to link EEG recordings to epileptic and non-epileptic subjects. These two studies required high computational load and could be addressed thanks to NeuralStudio. From a medical perspective, both methods proved the merits of NeuralStudio in brain research applications. For its outstanding features, NeuralStudio has been recently awarded a patent (US patent No. 7502763).

Ferramenta para avaliação e inferência de parâmetros de redes industriais sem fio

Wireless sensor networks (WSN) have gained ground in the industrial environment, due to the possibility of connecting points of information that were inaccessible to wired networks. However, there are several challenges in the implementation and acceptance of this technology in the industrial environment, one of them the guaranteed availability of information, which can be influenced by various parameters, such as path stability and power consumption of the field device. As such, in this work was developed a tool to evaluate and infer parameters of wireless industrial networks based on the WirelessHART and ISA 100.11a protocols. The tool allows quantitative evaluation, qualitative evaluation and evaluation by inference during a given time of the operating network. The quantitative and qualitative evaluation are based on own definitions of parameters, such as the parameter of stability, or based on descriptive statistics, such as mean, standard deviation and box plots. In the evaluation by inference uses the intelligent technique artificial neural networks to infer some network parameters such as battery life. Finally, it displays the results of use the tool in different scenarios networks, as topologies star and mesh, in order to attest to the importance of tool in evaluation of the behavior of these networks, but also support possible changes or maintenance of the system.

Glia-augmented artificial neural networks: foundations and applications

Information processing in the human brain has always been considered as a source of inspiration in Artificial Intelligence; in particular, it has led researchers to develop different tools such as artificial neural networks. Recent findings in Neurophysiology provide evidence that not only neurons but also isolated and networks of astrocytes are responsible for processing information in the human brain. Artificial neural net- works (ANNs) model neuron-neuron communications. Artificial neuron-glia networks (ANGN), in addition to neuron-neuron communications, model neuron-astrocyte con- nections. In continuation of the research on ANGNs, first we propose, and evaluate a model of adaptive neuro fuzzy inference systems augmented with artificial astrocytes. Then, we propose a model of ANGNs that captures the communications of astrocytes in the brain; in this model, a network of artificial astrocytes are implemented on top of a typical neural network. The results of the implementation of both networks show that on certain combinations of parameter values specifying astrocytes and their con- nections, the new networks outperform typical neural networks. This research opens a range of possibilities for future work on designing more powerful architectures of artificial neural networks that are based on more realistic models of the human brain.

Neural Network Evidence for the Coupling of Presaccadic Visual Remapping to Predictive Eye Position Updating.

As we look around a scene, we perceive it as continuous and stable even though each saccadic eye movement changes the visual input to the retinas. How the brain achieves this perceptual stabilization is unknown, but a major hypothesis is that it relies on presaccadic remapping, a process in which neurons shift their visual sensitivity to a new location in the scene just before each saccade. This hypothesis is difficult to test in vivo because complete, selective inactivation of remapping is currently intractable. We tested it in silico with a hierarchical, sheet-based neural network model of the visual and oculomotor system. The model generated saccadic commands to move a video camera abruptly. Visual input from the camera and internal copies of the saccadic movement commands, or corollary discharge, converged at a map-level simulation of the frontal eye field (FEF), a primate brain area known to receive such inputs. FEF output was combined with eye position signals to yield a suitable coordinate frame for guiding arm movements of a robot. Our operational definition of perceptual stability was "useful stability," quantified as continuously accurate pointing to a visual object despite camera saccades. During training, the emergence of useful stability was correlated tightly with the emergence of presaccadic remapping in the FEF. Remapping depended on corollary discharge but its timing was synchronized to the updating of eye position. When coupled to predictive eye position signals, remapping served to stabilize the target representation for continuously accurate pointing. Graded inactivations of pathways in the model replicated, and helped to interpret, previous in vivo experiments. The results support the hypothesis that visual stability requires presaccadic remapping, provide explanations for the function and timing of remapping, and offer testable hypotheses for in vivo studies. We conclude that remapping allows for seamless coordinate frame transformations and quick actions despite visual afferent lags. With visual remapping in place for behavior, it may be exploited for perceptual continuity.

A survey of intrusion detection system technologies

This paper provides an overview of IDS types and how they work as well as configuration considerations and issues that affect them. Advanced methods of increasing the performance of an IDS are explored such as specification based IDS for protecting Supervisory Control And Data Acquisition (SCADA) and Cloud networks. Also by providing a review of varied studies ranging from issues in configuration and specific problems to custom techniques and cutting edge studies a reference can be provided to others interested in learning about and developing IDS solutions. Intrusion Detection is an area of much required study to provide solutions to satisfy evolving services and networks and systems that support them. This paper aims to be a reference for IDS technologies other researchers and developers interested in the field of intrusion detection.

Existence and wandering of bumps in a spiking neural network model

We study spatially localized states of a spiking neuronal network populated by a pulse coupled phase oscillator known as the lighthouse model. We show that in the limit of slow synaptic interactions in the continuum limit the dynamics reduce to those of the standard Amari model. For non-slow synaptic connections we are able to go beyond the standard firing rate analysis of localized solutions allowing us to explicitly construct a family of co-existing one-bump solutions, and then track bump width and firing pattern as a function of system parameters. We also present an analysis of the model on a discrete lattice. We show that multiple width bump states can co-exist and uncover a mechanism for bump wandering linked to the speed of synaptic processing. Moreover, beyond a wandering transition point we show that the bump undergoes an effective random walk with a diffusion coefficient that scales exponentially with the rate of synaptic processing and linearly with the lattice spacing.