Excellent Noise Tolerance Research Articles

Task-Adaptive Neuromorphic Computing Using Reconfigurable Organic Neuristors with Tunable Plasticity and Logic-in-Memory Operations.

The brain's function can be dynamically reconfigured through a unified neuron-synapse architecture, enabling task-adaptive network-level topology for energy-efficient learning and inferencing. Here, we demonstrate an organic neuristor utilizing a ferroelectric-electrolyte dielectric interface. This neuristor enables tunable short- to long-term plasticity and reconfigurable logic-in-memory functions by controlling the interfacial interaction between electrolyte ions and ferroelectric dipoles. Notably, the short-term plasticity of the organic neuristor allows for power-efficient reservoir computing in edge-computing scenarios, exhibiting impressive recognition accuracy, including images (90.6%) and acoustic signals (97.7%). For high-performance computing tasks, the neuristor based on long-term plasticity and logic-in-memory operations can construct all of the hardware circuits of a binarized neural network (BNN) within a unified framework. The BNN demonstrates excellent noise tolerance, achieving high recognition accuracies of 99.2% and 86.4% on the MNIST and CIFAR-10 data sets, respectively. Consequently, our research sheds light on the development of power-efficient artificial intelligence systems.

General framework for genuine multipartite entanglement detection

Design of detection strategies for multipartite entanglement stands as a central importance on our understanding of fundamental quantum mechanics and has had substantial impact on quantum information applications. However, accurate and robust detection approaches are severely hindered, particularly when the number of nodes grows rapidly like in a quantum network. Here we present an exquisite procedure that generates novel entanglement witness for arbitrary targeted state via a generic and operational framework. The framework enjoys a systematic and high-efficient character and allows to substantiate genuine multipartite entanglement for a variety of states that arise naturally in practical situations, and to dramatically outperform currently standard methods. With excellent noise tolerance, our framework should be broadly applicable to witness genuine multipartite entanglement in various practically scenarios, and to facilitate making the best use of entangled resources in the emerging area of quantum network.

Method for assessing the characteristics of the quality of service of networks

Variational quantum algorithms are at the forefront of modeling fault-tolerant quantum devices of the near future. While most variational quantum algorithms use only continuous optimization variables, their representative power can sometimes be greatly increased by adding certain discrete optimization variables, as illustrated by the example of the generalized quantum approximation optimization algorithm. However, the hybrid discrete-continuous optimization problem poses an optimization problem. The paper proposes a new algorithm that combines the Monte Carlo tree search method with an improved gradient solver to optimize discrete and continuous variables in a quantum circuit, respectively. The algorithm has been found to have excellent noise tolerance properties and is superior to prior algorithms in the field.

Quaternion Projection Rule for Rotor Hopfield Neural Networks.

A rotor Hopfield neural network (RHNN) is an extension of a complex-valued Hopfield neural network (CHNN) and has excellent noise tolerance. The RHNN decomposition theorem says that an RHNN decomposes into a CHNN and a symmetric CHNN. For a large number of training patterns, the projection rule for RHNNs generates large self-feedbacks, which deteriorates the noise tolerance. To remove self-feedbacks, we propose a projection rule using quaternions based on the decomposition theorem. Using computer simulations, we show that the quaternion projection rule improves noise tolerance.

Diagonal rotor Hopfield neural networks

A complex-valued Hopfield neural network (CHNN) is a multistate Hopfield model and has been applied to the storage of image data. It has the weak noise tolerance due to the inherent property of rotational invariance. A hyperbolic-valued Hopfield neural network (HHNN) resolves rotational invariance and improves the noise tolerance. A rotor Hopfield neural network (RHNN) is an extension of CHNN and the weights are represented by matrices. It provides excellent noise tolerance by resolving the rotational invariance. However, an RHNN needs double weight parameters of a CHNN, unlike an HHNN. In this work, we propose a diagonal RHNN (DRHNN), which restricts the weights of RHNN to diagonal matrices and reduces the number of weight parameters. The number of weight parameters in a DRHNN, an HHNN, and a CHNN is same. In addition, a DRHNN resolves the rotational invariance and provides excellent noise tolerance like an RHNN.

Identification of Sudden Stiffness Change in the Acceleration Response of a Nonlinear Hysteretic Structure

The integration of discrete wavelet transform and independent component analysis (DWT-ICA) method can directly identify time-varying changes in linear structures. However, better metrics of structural seismic damage and future performance after an event are related to structural permanent and total plastic deformations. This study proposes a two-stage technique based on DWT-FastICA and improved multiparticle swarm coevolution optimization (IMPSCO) using a baseline nonlinear Bouc–Wen structural model to directly identify changes in stiffness caused by damage as well as plastic or permanent deflections. In the first stage, the measured structural dynamic responses are preprocessed firstly by DWT, and then the Fast ICA is used to extract the feature components that contain the damage information for the purpose of initially locating damage. In the second stage, the structural responses are divided at the identified damage instant into segments that are used to identify the time-varying physical parameters by using the IMPSCO, and the location and extent of damage can accordingly be identified accurately. The efficiency of the proposed method in identifying stiffness changes is assessed under different ground motions using a suite of two different ground acceleration records. Meanwhile, the effect of noise level and damage extent on the proposed method is also analyzed. The results show that in a realistic scenario with fixed filter tuning parameters, the proposed approach identifies stiffness changes within 1.25% of true stiffness within 8.96 s; therefore, it can work in real time. Parameters are identified within 14% of the actual as-modeled value using noisy simulation-derived structural responses. This indicates that, in accordance with different demands, the proposed method can not only locate and quantify damage within a short time with a high precision but also has excellent noise tolerance, robustness, and practicality.

Structural damage detection considering sensor performance degradation and measurement noise effect

In the real civil structures, material deterioration, overloading and environmental corrosion inevitably lead to sensor performance degradation or sensor fault. Sensor performance degradation or sensor fault usually introduce observable changes in the measured structural responses, which may be incorrectly interpreted as structural damage. This paper proposes a novel approach to quickly distinguish sensor fault from structural damage and locate the faulty or degraded sensors. Two steps are involved in this approach. In the first step, the root mean square of the generalized likelihood ratio test (GLRT) is used to detect and localize the structural damage or degraded sensors. In the second step, a new index is proposed used along with the statistical process control chart to distinguish sensor performance degradation from structural damage. The proposed index is the percentage of the extreme value of the largest principal component scores of the generalized likelihood ratio, which not only has excellent noise tolerance but also can distinguish sensor performance degradation from structural damage. The applicability and efficiency of the proposed approach are validated by numerical studies on a planar 11-element truss structure and experimental studies on a simply-supported steel beam in the laboratory. The results demonstrate that the proposed approach can locate the damage accurately when taking into account of sensor performance degradation and environmental noise in the measurements. The proposed index is able to accurately and quickly determine the source of the novelty in the responses.

Storage capacity of rotor Hopfield neural networks

Abstract Hopfield neural networks have been studied by many researchers. A complex-valued Hopfield neural network (CHNN) is a multistate model of Hopfield neural network, and has been applied to the storage of multilevel data, such as image data. A rotor Hopfield neural network (RHNN) is an extension of CHNN. The RHNNs demonstrated double the storage capacity of CHNNs and excellent noise tolerance by computer simulations. Jankowski et al. analyzed the storage capacity of CHNNs by approximating the crosstalk term using central limit theorem. In this work, we show that the RHNNs have double the storage capacity of the CHNNs based on their theory.

Max-plus and min-plus projection autoassociative morphological memories and their compositions for pattern classification

Autoassociative morphological memories (AMMs) are robust and computationally efficient memory models with unlimited storage capacity. In this paper, we present the max-plus and min-plus projection autoassociative morphological memories (PAMMs) as well as their compositions. Briefly, the max-plus PAMM yields the largest max-plus combination of the stored vectors which is less than or equal to the input. Dually, the vector recalled by the min-plus PAMM corresponds to the smallest min-plus combination which is larger than or equal to the input. Apart from unlimited absolute storage capacity and one step retrieval, PAMMs and their compositions exhibit an excellent noise tolerance. Furthermore, the new memories yielded quite promising results in classification problems with a large number of features and classes.

Rotational invariance of quaternionic hopfield neural networks

High‐dimensional neural networks have been studied by many researchers for their flexible representation. Quaternionic Hopfield neural networks (QHNNs) are one of them. Quaternions have the inherent property of non‐commutative multiplication. Connection weights act differently from left and right in QHNNs, and we can have left QHNNs (LQHNNs) and right QHNNs (RQHNNs). Hybrid QHNNs (HQHNNs), which are the compound models of LQHNNs and RQHNNs, have been proposed, and their excellent noise tolerance has been shown through computer simulations. It has been pointed out that the improvement in their noise tolerance is related to the avoidance of rotational invariance. Thus, it is very important to study rotational invariance. In this paper, we investigate the rotational invariance of QHNNs. Rotational invariance in LQHNNs and RQHNNs is different. We define the left and right‐rotated vectors, which are fixed in RQHNNs and LQHNNs, respectively. From the standpoint of HQHNNs, the common rotated vectors are important. We also study the common rotated vectors and provide a couple of exceptional examples. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Complex-Valued Recurrent Correlation Neural Networks.

In this paper, we generalize the bipolar recurrent correlation neural networks (RCNNs) of Chiueh and Goodman for patterns whose components are in the complex unit circle. The novel networks, referred to as complex-valued RCNNs (CV-RCNNs), are characterized by a possible nonlinear function, which is applied on the real part of the scalar product of the current state and the original patterns. We show that the CV-RCNNs always converge to a stationary state. Thus, they have potential application as associative memories. In this context, we provide sufficient conditions for the retrieval of a memorized vector. Furthermore, computational experiments concerning the reconstruction of corrupted grayscale images reveal that certain CV-RCNNs exhibit an excellent noise tolerance.

Fault diagnosis in assembly processes based on engineering-driven rules and PSOSAEN algorithm

The ability to detect and isolate process fault for product quality control in assembly processes plays an essential role in the success of a manufacturing enterprise in today’s globally competitive marketplace. However, the complexity of assembly processes makes it fairly challenging to diagnose process faults. One novel fixture fault diagnosis methodology has been developed in this study. The relationship between fixture fault patterns and part variation motion patterns is firstly off-line built, then | S| control chart is used as the detector of abnormal signals, and an improved Particle Swarm Optimization with Simulated Annealing-based selective neural network Ensemble (PSOSAEN) algorithm is explored for on-line identifying the part variation motion patterns triggering the out-of-control signals. Finally, an unknown fixture fault is identified based on the output of PSOSAEN algorithm and explored diagnosis rules. The method has excellent noise tolerance in real time, requires no hypothesis on statistical distribution of measurements, and has explicit engineering interpretation of the diagnostic process. The data from the real-world aircraft horizontal stabilizer assembly process were collected to validate the developed methodology. The analysis results indicate that the developed diagnosis methodology can perform effectively for fixture fault diagnosis in assembly processes. All of the analysis from this study provides guidelines in developing selective neural network ensemble and statistical process control-based fault diagnosis systems with integration of engineering knowledge in assembly processes.

Using Minimum Quantization Error chart for the monitoring of process states in multivariate manufacturing processes

The need for multivariate statistical process control (MSPC) becomes more important as several variables should be monitored simultaneously. MSPC is implemented using a variety of techniques including neural networks (NNs). NNs have excellent noise tolerance in real time, requiring no hypothesis on statistical distribution of monitored processes. This feature makes NNs promising tools used for monitoring process changes. However, major NNs applied in SPC are based on supervised learning, which limits their wide applications. In the paper, a Self-Organizing Map (SOM)-based process monitoring approach is proposed for enhancing the monitoring of manufacturing processes. It is capable to provide a comprehensible and quantitative assessment value for current process state, which is achieved by the Minimum Quantization Error ( MQE) calculation. Based on these MQE values over time series, an MQE chart is developed for monitoring process changes. The performance of MQE chart is analyzed in a bivariate process under the assumption that the predictable abnormal patterns are not available. The performance of MQE is further evaluated in a semiconductor batch manufacturing process. The experimental results indicate that MQE charts can become an effective monitoring and analysis tool for MSPC.

Identifying source(s) of out-of-control signals in multivariate manufacturing processes using selective neural network ensemble

In multivariate statistical process control (MSPC), most multivariate quality control charts are shown to be effective in detecting out-of-control signals based upon an overall statistic. But these charts do not relieve the need for pinpointing source(s) of the out-of-control signals. Neural networks (NNs) have excellent noise tolerance and high pattern identification capability in real time, which have been applied successfully in MSPC. This study proposed a selective NN ensemble approach DPSOEN, where several selected NNs are jointly used to classify source(s) of out-of-control signals in multivariate processes. The immediate location of the abnormal source(s) can greatly narrow down the set of possible assignable causes, facilitating rapid analysis and corrective action by quality operators. The performance of DPSOEN is analyzed in multivariate processes. It shows improved generalization performance that outperforms those of single NNs and Ensemble All approach. The investigation proposed a heuristic approach for applying the DPSOEN-based model as an effective and useful tool to identify abnormal source(s) in bivariate statistical process control (SPC) with potential application for MSPC in general.

Using an MQE chart based on a self-organizing map NN to monitor out-of-control signals in manufacturing processes

Control charts are recognized as one of the most important tools for statistical process control (SPC), used for monitoring any abnormal deviations in the state of manufacturing processes. However, the effectiveness of control charts is strictly dependent on statistical assumptions that in real applications are frequently violated. In contrast, neural networks (NNs) have excellent noise tolerance in real time, requiring no hypothesis on the statistical distribution of monitored processes. This feature makes NNs promising tools for quality control. In this paper, a self-organizing map (SOM)-based monitoring approach is proposed for enhancing the monitoring of processes. It is capable of providing a comprehensive and quantitative assessment value for the current process state, achieved by minimum quantization error (MQE) calculation. Based on MQE values over time series, a novel MQE chart is developed for monitoring process changes. The aim of this research is to analyse the performance of the MQE chart under the assumption that predictable abnormal patterns are not available. To this aim, the performance of the MQE chart in manufacturing processes (including non-correlated, auto-correlated and multivariate processes) is evaluated. The results indicate that the MQE chart may be a promising tool for quality control.

Using emerging patterns to construct weighted decision trees

Decision trees (DTs) represent one of the most important and popular solutions to the problem of classification. They have been shown to have excellent performance in the field of data mining and machine learning. However, the problem of DTs is that they are built using data instances assigned to crisp classes. In this paper, we generalize decision trees so that they can take into account weighted classes assigned to the training data instances. Moreover, we propose a novel method for discovering weights for the training instances. Our method is based on emerging patterns (EPs). EPs are those itemsets whose supports (probabilities) in one class are significantly higher than their supports (probabilities) in the other classes. Our experimental evaluation shows that the new proposed method has good performance and excellent noise tolerance.

Prediction of consumer liking from trained sensory panel information: Evaluation of neural networks

This study was set out to establish artificial neural networks (ANN) as an alternative to regression methods (multiple linear, principal component and partial least squares regression) to predict consumer liking from trained sensory panel data. The sensory profile and acceptability of 10 market samples of beef bouillon products were measured. The products were distinct as evaluated by the trained sensory panel. A total of 100 regular beef bouillon product users from Manila measured overall liking, flavour, aftertaste and mouthfeel of the products. Curve fitting method was applied to identify sensory drivers of consumer liking. The sensory drivers of consumer liking were used as explanatory variables in artificial neural networks and regression methods. To overcome the limitations of regression methods we have used artificial neural network techniques to model consumer liking score as a function of trained sensory panel scores and achieved quite encouraging results. Our simulation experiments show that though the regression methods such as multiple linear regression (MLR), principal component regression (PCR) and partial least square (PLS) give an accurate prediction of consumer liking scores, this approach is not robust enough to handle the variations normally encountered in trained sensory panel data. ANNs were trained using the sensory panel raw data and transformed data. The networks trained with sensory panel raw data achieved 98% correct learning, the testing was in a range of 28–35%. Suitable transformation method was applied to reduce the variations in trained sensory panel raw data. The networks trained with transformed sensory panel data achieved about 80–90% correct learning and 80–95% correct testing. It is shown that due to its excellent noise tolerance property and ability to predict more than one type of consumer liking using a single model, the ANN approach promises to be an effective modelling tool.

Optimal incoherent correlator for noisy gray-tone image recognition

An optical transfer function consisting of a phase-only term and an optimized passband is synthesized for constructing an incoherent optical correlator for recognition of a noisy gray-tone image. The proposed incoherent correlator can yield a sharp correlation peak with excellent noise tolerance.

Design of optimal phase-only filters by direct iterative search

A fast algorithm termed the direct iterative search (DIS) is proposed to design the optimal phase-only filters (POFs) with a high Horner efficiency and high-signal-to-noise ratio (SNR). The DIS optimizes the phase and passband of POF in the sense of maximizing the correlation peak of the signal image and minimizing the noise passage. Simulation results show the capability of the DIS for achieving a satisfactory optimum of filter phase and passband. The optimized POFs by the DIS show sharp, high correlation peak and excellent noise tolerance.