Second-order Neural Network Research Articles

A Novel Iterative Second-Order Neural-Network Learning Control Approach for Robotic Manipulators

A Novel Iterative Second-Order Neural-Network Learning Control Approach for Robotic Manipulators

Cognitive computing models for estimation of reference evapotranspiration: A review

Irrigation practices can be advanced by the aid of cognitive computing models. Repeated droughts, population expansion and the impact of global warming collectively impose rigorous restrictions over irrigation practices. Reference evapotranspiration (ET0) is a vital factor to predict the crop water requirements based on climate data. There are many techniques available for the prediction of ET0. An efficient ET0 prediction model plays an important role in irrigation system to increase water productivity. In the present study, a review has been carried out over cognitive computing models used for the estimation of ET0. Review exhibits that artificial neural network (ANN) approach outperforms support vector machine (SVM) and genetic programming (GP). Second order neural network (SONN) is the most promising approach among ANN models.

Learning Feedforward Control Using Multiagent Control Approach for Motion Control Systems

Multiagent control system (MACS) has become a promising solution for solving complex control problems. Using the advantages of MACS-based design approaches, a novel solution for advanced control of mechatronic systems has been developed in this paper. The study has aimed at integrating learning control into MACS. Specifically, learning feedforward control (LFFC) is implemented as a pattern for incorporation in MACS. The major novelty of this work is that the feedback control part is realized in a real-time periodic MACS, while the LFFC algorithm is done on-line, asynchronously, and in a separate non-real-time aperiodic MACS. As a result, a MACS-based LFFC design method has been developed. A second-order B-spline neural network (BSN) is used as a function approximator for LFFC whose input-output mapping can be adapted during control and is intended to become equal to the inverse model of the plant. To provide real-time features for the MACS-based LFFC system, the open robot control software (OROCOS) has been employed as development and runtime environment. A case study using a simulated linear motor in the presence of nonlinear cogging and friction force as well as mass variations is used to illustrate the proposed method. A MACS-based LFFC system has been designed and implemented for the simulated plant. The system consists of a setpoint generator, a feedback controller, and a time-index LFFC that can learn on-line. Simulation results have demonstrated the applicability of the design method.

Super-twisting-based continuous neural networks modelling of second-order interconnected systems

ABSTRACTThe aim of this work was to design a non-parametric model of interconnected systems represented by uncertain second-order systems with incomplete information (only the generalized position vector is measurable). Artificial neural networks appeared to be a plausible alternative to get a non-parametric representation of the aforementioned interconnected systems. The modelling strategy used a set of spatial distributed second-order continuous neural networks (CNN). Each node in the interconnected system was represented as a second-order continuous neural network added by the super-twisting discontinuous sliding mode algorithm. The non-parametric modelling problem was reduced to design a feasible expression for the CNN weights in order to reproduce the states (including the generalized derivative of position vector) of all the nodes dynamics together and simultaneously. The adaptive laws for the CNN weights ensured the convergence of the CNN trajectories to the states of the uncertain interconnected system. To investigate the qualitative behaviour of the suggested methodology, two numerical examples were proposed. The first one represents the interconnection of three mass–spring–damper mechanical systems. The second example considers the problem of the non-parametric modelling problem for a wave partial differential equation. A set of three-dimensional graphic representations were used to demonstrate the identification abilities achieved by the CNN designed in this study for the second case.

Evapotranspiration Modeling Using Second-Order Neural Networks

This study introduces the utility of the second-order neural network (SONN) method to model the reference evapotranspiration (ET0) in different climatic zones of India. The daily climate data of minimum and maximum air temperatures, minimum and maximum relative humidity, wind speed, and solar radiation from 17 different locations in India were used as the inputs to the SONN models to estimate ET0 corresponding to the FAO-56 Penman-Monteith (FAO-56 PM) method. With the same inputs, for all 17 locations the first-order neural networks such as feed forward back propagation (FFBP-NN) models were also developed and compared with the SONN models. The developed SONN and FFBP-NN models were also compared with the estimates provided by the FAO-56 PM method. The performance criteria adopted for comparing the models were root-mean-squared error (RMSE), mean-absolute error (MAE), coefficient of determination (R2), and the ratio of average output to average target ET0 values (Rratio). Based on the comparisons, it is concluded that the SONN models applied successfully to model ET0 and performed better compared to the FFBP-NN models. This study also found that the SONN models yield better results using a fewer number of hidden neurons compared to FFBP-NN models. Better performance of SONN over FFBP-NN models suggest that SONN models can be used to estimate ET0 in different climatic zones of India.

Simultaneously emerging Braitenberg codes and compositionality

Although many researchers have suggested that compositional concepts should be sensorimotor grounded, the method to accomplish this remains unclear. This article introduces a second-order neural network with parametric biases (sNNPB) that learns compositional structures based on sensorimotor time series data. The data was produced by a simulated robot that executed distinct object interactions (move-to and orient-toward). We show that various sNNPB setups can learn to compositionally imitate object interactions beyond the interactions that were specifically trained, which was not possible with previous neural network (NN) architectures, including recurrent neural networks (RNNs). We also show that these imitation capabilities are accomplished by developing a self-organized, geometrically arranged compositional concept structure in the PB values and task-oriented, Braitenberg-like sensory encodings in hidden sensory layers. Because second-order connections were necessary to accomplish the task, we hypothesize that such connections may be essential to drive the learning of both sensorimotor-grounded compositional structures and Braitenberg-like, behavior-oriented ‘‘pro-presentations.’’ From a cognitive perspective, we show how sensorimotor time series of interactions may be processed to generate the signals necessary to develop semantically compositional structures.

A flexible visual inspection system based on neural networks

In this work, we propose a neural networks-based machine vision system, which is intended to act as a reconfigurable inspection tool, for use in manufacturing environments. The processing engine of the system is a second-order neural network, which extracts geometric features invariant to translation and rotation. A major issue with the use of higher-order neural networks is the combinatorial explosion of the higher-order terms, which is addressed here with the use of the alternative image representation strategy of coarse coding. We developed a genetic algorithms tool, which allows the automated determination of the optimal number of hidden units in the neural networks architecture. The inspection system is tested in two application areas, namely inspection of axisymmetric components and classification of rivets. Numerous tests are carried out to evaluate the robustness of the proposed system to complex noise sources.

Fuzzy Automata Induction using Construction Method

Recurrent neural networks have recently been demonstrated to have the ability to learn simple grammars. In particular, networks using second-order units have been successfully at this task. However, it is often difficult to predict the optimal neural network size to induce an unknown automaton from examples. Instead of just adjusting the weights in a network of fixed topology, we adopt the dynamic networks (i.e. the topology and weights can be simultaneously changed during training) for this application. We apply the idea of maximizing correlation in the cascade-correlation algorithm to the second-order single-layer recurrent neural network to generate a new construction algorithm and use it to induce fuzzy finite state automata. The experiment indicates that such a dynamic network performs well.

Motion Feature Extraction Using Second-order Neural Network and Self-organizing Map for Gesture Recognition

Motion Feature Extraction Using Second-order Neural Network and Self-organizing Map for Gesture Recognition

Small hydro power plant identification using NNARX structure

A feedforward multi-layer perceptron neural network structure is developed to model the nonlinear dynamic relationship between input and output of a hydro power plant connected as single machine infinite bus system. Two independent second-order neural network nonlinear auto-regressive with exogenous signal models are used in the study. The structure selection of each independent model is based on various validation tests. The optimal brain surgeon pruning strategy adopted for optimizing the neural network structure. The network performance is studied for fixed and change in operating point.

Motion Feature Extraction Using Second-order Neural Network and Self-organizing Map for Gesture Recognition

††† We propose a neural preprocess approach for video-based gesture recognition system. Second-order neural network (SONN) and self-organizing map (SOM) are employed for extracting moving hand regions and for normalizing motion features respectively. The SONN is more robust to noise than frame difference technique. Obtained velocity feature vectors are translated into normalized feature space by the SOM with keeping their topology, and the transition of the activated node in the topological map is classified by DP matching. The topological nature of the SOM is quite suited to data normalization for the DP matching technique. Experimental results show that those neural networks effectively work on the gesture pattern recognition. The SONN shows its noise reduction ability for noisy backgrounds, and the SOM provides the robustness to spatial scaling of input images. The robustness of the SOM to spatial scaling is based on its robustness to velocity scaling.

On a higher-order neural network for distortion invariant pattern recognition

This paper proposed some methods upon a second-order neural network. These networks apply the normalized frequency distribution of distance between two points on an object. 0.766 of the recognition accuracy for 2D two-class mixture distributions and 0.960 for hand-written characters are achieved.

Second-order optical neural network with free-space interconnections

Second-order optical neural network with free-space interconnections

Radar image segmentation using self-adapting recurrent networks.

This paper presents a novel approach to the segmentation and integration of (radar) images using a second-order recurrent artificial neural network architecture consisting of two sub-networks: a function network that classifies radar measurements into four different categories of objects in sea environments (water, oil spills, land and boats), and a context network that dynamically computes the function network's input weights. It is shown that in experiments (using simulated radar images) this mechanism outperforms conventional artificial neural networks since it allows the network to learn to solve the task through a dynamic adaptation of its classification function based on its internal state closely reflecting the current context.

Translation, scale and rotation invariant pattern recognition using Principal Component Analysis (PCA) and reduced second-order neural network

Translation, scale and rotation invariant pattern recognition using Principal Component Analysis (PCA) and reduced second-order neural network

Optical implementation of a translation-invariant second-order neural network for multiple-pattern classification

A novel approach to the optical implementation of second-order neural networks that can recognize multiple patterns is reported. The systems issues, especially the accuracy required for the weighted interconnections, are discussed for numeric character (0-9) recognition. It is shown that the accuracy of the weighted interconnections has a far greater influence on the network performance during training than on classification. To lessen the problem, we introduce an adaptive learning rule, whereby the optical power is adjusted during training. Finally, numeric character recognition using an experimental system with a liquid-crystal display is demonstrated.

Application of high-order neural networks in chemistry

The effectiveness and usefulness of the so-called high-order neural networks for classification of chemical objects is demonstrated. The high-order neural networks usually do not need hidden neurons for correct interpretation of patterns. A simple formula for partial derivatives of the minimized objective (error) function is derived, which is used for production of weight coefficients during the adaptation process. An illustrative example dealing with inductive and resonance effects of functional groups by the second-order neural network is presented.

Convergence Time and Memory Capacity of Higher-order Hopfield Associative Memory with Multi-valued Neurons

We investigate the two basic properties, i.e. convergence time and memory capacity, or the higher-order Hopfield associative memory with multi-valued neurons. The second-order Hopfield neural network or multi-valued neurons is presented analytically. The properties or the combined higher-order multi-valued model is then studied. Finally, the memory capacity or the higher-higher order binary-valued model is studied using a statistical approach

Scale and rotation invariant pattern recognition using complex-log mapping and augmented second order neural network

A scale and rotation invariant pattern recognition system using complex-log mapping (CLM) and an augmented second order neural network (SONN) is proposed. CLM is very useful for extracting the scale and rotation invariant features. The results are, however, given in a wrap-around translated form. This problem is solved with an augmented SONN. Experimental results show that the proposed system has improved recognition performance.

Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks

We show that a recurrent, second-order neural network using a real-time, forward training algorithm readily learns to infer small regular grammars from positive and negative string training samples. We present simulations that show the effect of initial conditions, training set size and order, and neural network architecture. All simulations were performed with random initial weight strengths and usually converge after approximately a hundred epochs of training. We discuss a quantization algorithm for dynamically extracting finite state automata during and after training. For a well-trained neural net, the extracted automata constitute an equivalence class of state machines that are reducible to the minimal machine of the inferred grammar. We then show through simulations that many of the neural net state machines are dynamically stable, that is, they correctly classify many long unseen strings. In addition, some of these extracted automata actually outperform the trained neural network for classification of unseen strings.