Input Weights Research Articles

Direct implementation of a perceptron in superconducting circuit quantum hardware

The utility of classical neural networks as universal approximators suggests that their quantum analogues could play an important role in quantum generalizations of machine-learning methods. Inspired by the proposal in Torrontegui and Garc\'{\i}a-Ripoll [Europhys. Lett. 125, 30004 (2019)], we demonstrate a superconducting qubit implementation of a controlled gate, which generalizes the action of a classical perceptron as the basic building block of a quantum neural network. In a two-qubit setup we show full control over the steepness of the perceptron activation function, the input weight and the bias by tuning the gate length, the coupling between the qubits, and the frequency of the applied drive, respectively. In its general form, the gate realizes a multiqubit entangling operation in a single step, whose decomposition into single- and two-qubit gates would require a number of gates that is exponential in the number of qubits. Its demonstrated direct implementation as perceptron in quantum hardware may therefore lead to more powerful quantum neural networks when combined with suitable additional standard gates.

Tactile temporal order judgment during rubber hand illusion: Distinct modulation of the point of subjective simultaneity and temporal resolution

During the rubber hand illusion (RHI), individuals feel a fake hand as their own (ownership) and a perceived position of their real hand shifts toward the fake hand (proprioceptive drift; PD), which represents updating of multisensory hand representations. Bimanual tactile temporal order judgment (TOJ) includes processes of localizing tactile stimuli in space, for which multisensory hand representations are essential. According to the common processes, we examined tactile TOJ performance during the RHI and non-RHI. Temporal resolution (TR) as TOJ accuracy worsened during the non-RHI compared to the RHI. Additionally, a significant correlation between TR and PD was observed only in the non-RHI condition. However, the point of subjective simultaneity (PSS), which offers relative weighting of tactile inputs from the right and left hands, was correlated with illusory hand ownership. These results suggest that PSS and TR from tactile TOJ during RHI relate to self-attribution and localization of the hand, respectively.

H-Infinity Loop-Shaped Model Predictive Control With HVAC Application

We formulate a model predictive control (MPC) for linear time-invariant systems based on H-infinity loop-shaping. The design results in a closed-loop system that includes a state estimator and attains an optimized stability margin. Input and output weights are designed in the frequency domain to satisfy steady-state and transient performance requirements, in lieu of standard MPC plant model augmentations. The H-infinity loop-shaping synthesis results in an observer-based state feedback structure. An inverse optimal control problem is solved to construct the MPC cost function, so that the control input computed by MPC is equal to the H-infinity control input when the constraints are inactive. The MPC inherits the closed-loop performance and stability margin of the loop-shaped design when constraints are inactive. We apply the methodology to a multizone heat pump, and validate the results in simulations and laboratory experiments. The design rejects constant unmeasured disturbances, tracks constant references with zero steady-state error, meets transient performance requirements, provides an excellent stability margin, and enforces input and output constraints.

Shear Sonic Prediction Based on DELM Optimized by Improved Sparrow Search Algorithm

In the geophysical exploration field, the sonic log (DT) and shear sonic log (DTS) are frequently used as quick and affordable procedures for reservoir evaluation. Due to the high acquisition costs, DTS is only accessible in a few wells within an oil/gas field. Numerous attempts have been made to establish a precise relationship between DTS and other petrophysical data. In this study, a method based on the deep extreme learning machine optimized by the improved sparrow search algorithm (ISSA-DELM) is proposed to improve the accuracy and stability of the DTS prediction. Firstly, the deep extreme learning machine (DELM) model is constructed by combining the extreme learning machine and the autoencoder algorithm. Secondly, aimed at the defects of the sparrow search algorithm (SSA), an improved sparrow search algorithm (ISSA) with the firefly search disturbance is proposed by merging the iterative strategy of the firefly algorithm and applied to optimize the initial input weights of the DELM. Finally, the ISSA-DELM is applied to the prediction of the DTS in a block of the Ordos Basin in China. The quantitative prediction results show that the RMSE, MAE, and R-square predicted by the ISSA-DELM model are 6.1255, 4.1369, and 0.9916, respectively. The comprehensive performance is better than the ELM, the DELM, and the DELM optimized by the optimization algorithms, such as the genetic algorithm (GA), the particle swarm optimization (PSO), and the SSA. Therefore, it can be concluded that the method provides an effective method for missing DTS estimation.

Clothing image classification algorithm based on convolutional neural network and optimized regularized extreme learning machine

This paper proposes a new method that uses Alexnet with ImageNet transfer learning as the feature extractor and optimized and regularized extreme learning as the classifier. We keep the first five convolutional layers and the first two fully connected layers of Alexnet, and then train the network. Then, the mutual information between each dimension of the feature and its category is calculated and sorted, and the feature with the highest ranking is selected for feature dimensionality reduction. The regularization penalty term is introduced to the extreme learning machine to control its algorithm complexity and solve the problem of overfitting. Finally, the Runge Kutta optimization algorithm is employed to ameliorate the hidden layer bias and input weight of the regularized extreme learning machine, and the optimized regularized extreme learning machine is used to classify the dimensionality-reduced clothing image traits. The test outcome illustrates that on some apparel classification with style (ACWS) datasets, the precision, recall, F1-score, and accuracy of the proposed algorithm are 93.06%, 93.17%, 92.82%, and 93.14%, respectively, which are better than those of other clothing image classification algorithms. The results verify that the raised algorithm significantly ameliorates the classification property of clothing image algorithms.

SELF-ORGANIZING RESERVOIR NETWORK FOR ACTION RECOGNITION

Current research in human action recognition (HAR) focuses on efficient and effective modelling of the temporal features of human actions in 3-dimensional space. Echo State Networks (ESNs) are one suitable method for encoding the temporal context due to its short-term memory property. However, the random initialization of the ESN's input and reservoir weights may increase instability and variance in generalization. Inspired by the notion that input-dependent self-organization is decisive for the cortex to adjust the neurons according to the distribution of the inputs, a Self-Organizing Reservoir Network (SORN) is developed based on Adaptive Resonance Theory (ART) and Instantaneous Topological Mapping (ITM) as the clustering process to cater deterministic initialization of the ESN reservoirs in a Convolutional Echo State Network (ConvESN) and yield a Self-Organizing Convolutional Echo State Network (SO-ConvESN). SORN ensures that the activation of ESN’s internal echo state representations reflects similar topological qualities of the input signal which should yield a self-organizing reservoir. In the context of HAR task, human actions encoded as a multivariate time series signals are clustered into clustered node centroids and interconnectivity matrices by SORN for initializing the SO-ConvESN reservoirs. By using several publicly available 3D-skeleton-based action recognition datasets, the impact of vigilance threshold and reservoir perturbation of SORN in performing clustering, the SORN reservoir dynamics and the capability of SO-ConvESN on HAR task have been empirically evaluated and analyzed to produce competitive experimental results.

Unraveling Functional Diversity of Cortical Synaptic Architecture Through the Lens of Population Coding.

The synaptic inputs to single cortical neurons exhibit substantial diversity in their sensory-driven activity. What this diversity reflects is unclear, and appears counter-productive in generating selective somatic responses to specific stimuli. One possibility is that this diversity reflects the propagation of information from one neural population to another. To test this possibility, we bridge population coding theory with measurements of synaptic inputs recorded in vivo with two-photon calcium imaging. We construct a probabilistic decoder to estimate the stimulus orientation from the responses of a realistic, hypothetical input population of neurons to compare with synaptic inputs onto individual neurons of ferret primary visual cortex (V1) recorded with two-photon calcium imaging in vivo. We find that optimal decoding requires diverse input weights and provides a straightforward mapping from the decoder weights to excitatory synapses. Analytically derived weights for biologically realistic input populations closely matched the functional heterogeneity of dendritic spines imaged in vivo with two-photon calcium imaging. Our results indicate that synaptic diversity is a necessary component of information transmission and reframes studies of connectivity through the lens of probabilistic population codes. These results suggest that the mapping from synaptic inputs to somatic selectivity may not be directly interpretable without considering input covariance and highlights the importance of population codes in pursuit of the cortical connectome.

Automated detection of offshore wave power using machine learning techniques

BackgroundVarious statistical methods are used for estimating sea state and wave characteristics using digital wave models. Several machine learning techniques help to develop the computational difficulties of these methods. Materials and methodsThis study aims to estimate the wave power with Extreme Learning Machine (ELM), Regression, Restricted Boltzmann Machine (RBM), and RBM-ELM methods using nonlinear wave input parameters at different depths. Furthermore, the performance criteria are improved by applying the Relief feature selection algorithm to these methods. The input bias and input weights for the ELM have been determined using the RBM. ResultsIn the RBM-based presented method, the highest estimation values were obtained using Relief feature selection and without Relief as 96.96% and 94.02%, respectively. The highest accuracy rate based on ELM is 76.86% in the estimation of wave power without Relief. In the same way, the accuracy rate with Relief was calculated as 92.16%. These values were increased to 90.10% (without Relief) and 95.73% (with Relief) using the RBM-ELM method. ConclusionsThis study demonstrates that the performance of the presented methods with Relief feature selection was improved.

Viscoelastic or Viscoplastic Glucose Theory (VGT #38): Applying VEGT or VPGT to Study Fasting Plasma Glucose (FPG) Versus Sleep, Weight, and HbA1C to Predict FPG Using Viscoelastic Perturbation Model over 13 Semi-Annual Periods from Y15H2 to Y21H2 Based on the GH-Method: Math-Physical Medicine (No. 619)

Since 2012, the author has been collecting his body weight and finger-piercing glucose values each day. In addition, he accumulates his medical conditions data including blood pressure (BP), heart rate(HR), and blood lipids along with lifestyle details of diet, exercise, sleep, stress, water intake and daily routine details. Based on the collected big data, he organized them into two main groups. The first group is the medical conditions (MC) with 4 categories: weight, glucose, BP, and lipids. The second group is the lifestyle details (LD) with 6 categories: food, exercise, water intake, sleep, stress, and daily routines. For this study, he collects his daily data and then calculates a unique score for each of the 10 categories, including weight (m1), sleep score (m7), and HbA1C. In this article, the author applies the viscoelasticity and viscoplasticity theories to conduct his research to discover some hidden behavior or relationship between fasting plasma glucose or FPG (as an output or strain) versus sleep, weight, or HbA1C (as inputs or stresses). The hidden behaviors and relationships between the output biomarker for FPG and the three selected input biomarkers, sleep, weight, and A1C, are time-dependent which change from time to time.

Financial efficiency of companies operating in the Kosovo food sector: DEA and DEAHP

Data Envelopment Analysis (DEA) evaluates a large number of input and output variables using mathematical programming techniques and analyzes the effectiveness of similar decision making units (DMU). Unlike traditional methods, the most important advantage of DEA is that the weights of input and output variables can be defined by the analyzer. In this study, the limitations of the DEA weights were determined using the AHP, which considers expert opinion. In addition, an alternative judgment scale was used for the Saaty judgment scale, which is used as a standard in the AHP method, and thus a more sensitive analysis was performed. There have been studies dealing with the comparison of judgment scales, but few studies on consistency sensitivity are needed. This point has also been addressed in this study. Subsequently, the financial efficiency of 27 companies operating in the food sector in Kosovo was evaluated with the weight-restricted DEA model, first created using the unweighted DEA model and then the AHP model, and the two models were compared. This paper is the first one of its kind since there are no previous studies regarding the examination of the financial efficiency of companies operating in the Kosovo food sector based on the DEAHP method.

Adaptive Spike-Like Representation of EEG Signals for Sleep Stages Scoring.

Recently there has seen promising results on auto-matic stage scoring by extracting spatio-temporal features from electroencephalogram (EEG). Such methods entail laborious manual feature engineering and domain knowledge. In this study, we propose an adaptive scheme to probabilistically encode, filter and accumulate the input signals and weight the resultant features by the half-Gaussian probabilities of signal intensities. The adaptive representations are subsequently fed into a transformer model to automatically mine the relevance between features and corresponding stages. Extensive exper-iments on the largest public dataset against state-of-the-art methods validate the effectiveness of our proposed method and reveal promising future directions.

SBNN: A Searched Binary Neural Network for SAR Ship Classification

The synthetic aperture radar (SAR) for ocean surveillance missions requires low latency and light weight inference. This paper proposes a novel small-size Searched Binary Network (SBNN), with network architecture search (NAS) for ship classification with SAR. In SBNN, convolution operations are modified by binarization technologies. Both input feature maps and weights are quantized into 1-bit in most of the convolution computation, which significantly decreases the overall computational complexity. In addition, we propose a patch shift processing, which can adjust feature maps with learnable parameters at spatial level. This process enhances the performance by reducing the information irrelevant to the targets. Experimental results on the OpenSARShip dataset show the proposed SBNN outperforms both binary neural networks from computer vision and CNN-based SAR ship classification methods. In particular, SBNN shows a great advantage in computational complexity.

Bagging–XGBoost algorithm based extreme weather identification and short-term load forecasting model

Accurate short-term load forecasting of distribution transformer in extreme weather will effectively assist power dispatching and enable safe and stable operation of power grid. Therefore, this paper proposes the Bagging–XGBoost algorithm based extreme weather identification and short-term load forecasting model, which can warn the time period and detailed value of peak load in advance. Firstly, based on Extreme Gradient Boosting (XGBoost) algorithm, the idea of Bagging is introduced to reduce the output variance and enhance the generalization ability of the algorithm. Then, the mutual information (MI) between weather influencing factors and load is analyzed to adjust the input weight of the model and improve its ability to track weather changes. Next, considering the load, weather and time factors, the extreme weather identification model is established to determine the occurrence range of peak load. Finally, the specialized training set is selected based on the weighted similarity, and high-accuracy short-term load forecasting model is established. Compared with the traditional model, the model proposed in this paper reduces the average Mean Absolute Percentage Error (MAPE) of peak load by 3% to 10%.

Ultra-short-term wind power prediction based on PVMD-ESMA-DELM

The non-linearity and non-stationarity of wind power data have brought great challenges to the safe operation of the power system. It is particularly important to effectively improve the accuracy of ultra-short-term prediction of wind power. Therefore, we propose an ultra-short-term wind power prediction method that particle swarm optimization-variational mode decomposition (PVMD), enhanced slime mold algorithm (ESMA) for elite opposition-based learning strategy (EOBL) and deep extreme learning machine (DELM). First, the particle swarm optimization algorithm (PSO) is used to optimize the two core parameters of the variational mode decomposition (VMD) to obtain the PVMD algorithm. The PVMD is used to decompose the original wind power data into a series of stable sub-sequences, and the rolling time series is used to analyze the sub-sequences decomposed by PVMD. Then the DELM predictive model is established and the input weights (e) and thresholds (bc) in DELM are optimized through ESMA, and the EOBL is used to improve the diversity and population quality of the slime mold population, thereby improving the global optimization performance and convergence accuracy of the slime mold algorithm (SMA), and further improving the prediction accuracy of the DELM model. Finally, each subsequence is substituted into the DELM optimized by the elite opposition based learning-slime mold algorithm (ESMA-DELM), and the prediction components are superimposed to obtain the final prediction result. Comparing the effects of several different forecasting models with the evaluation of calculation examples proves the effectiveness of the PVMD-ESMA-DELM blended forecasting model proposed in this paper, and gives a new approach for ultra-short-term wind power prediction.

Power-Efficient Deep Neural Network Accelerator Minimizing Global Buffer Access without Data Transfer between Neighboring Multiplier—Accumulator Units

This paper presents a novel method for minimizing the power consumption of weight data movements required by a convolutional operation performed on a two-dimensional multiplier–accumulator (MAC) array of a deep neural-network accelerator. The proposed technique employs a local register file (LRF) at each MAC unit in a manner such that once weight pixels are read from the global buffer into the LRF, they are reused from the LRF as many times as desired instead of being repeatedly fetched from the global buffer in each convolutional operation. One of the most evident merits of the proposed method is that the procedure is completely free from the burden of data transfer between neighboring MAC units. It was found from our simulations that the proposed method provides a power saving of approximately 83.33% and 97.62% compared with the power savings recorded by the conventional methods, respectively, when the dimensions of the input data matrix and weight matrix are 128 × 128 and 5 × 5, respectively. The power savings increase as the dimensions of the input data matrix or weight matrix increase.

XNOR-Nets with SETs: Proposal for a binarised convolution processing elements with Single-Electron Transistors

Deep neural network (DNN) and Convolution neural network (CNN) algorithms have significantly increased the accuracies in cutting-edge large-scale image recognition and natural-language processing tasks. Generally, such neural nets are implemented on power-hungry GPUs, beyond the reach of low-power edge-devices. The binary neural nets have been proposed recently, where both the input activations and weights are constrained to + 1 and − 1 to address this challenge. Here in the present proof-of-concept study, we propose a simple class of mixed-signal circuits composed of single-electron devices and exploit the nonlinear Coulomb staircase phenomena to alleviate the challenges of binarised deep learning hardware accelerators. In particular, through SPICE modeling, we demonstrate the realisation of space-time-energy efficient XNOR-Accumulation (XAC) operation, reconfigurabilty of XAC circuit to perform 1D convolution and a busbar design to augment a contemporary accelerator. These nanoscale circuits could be readily fabricated and may potentially be deployed in low-power deep-learning systems.

Fractal adaptive weight synthesized-local directional pattern-based image classification using enhanced tree seed algorithm.

Coral reefs are one of the most prominent marine ecosystems on the Earth; they are threatened due to various factors, including growing anthropogenic impacts and the effects of global change. Hence, the automatic classification of coral species is significant for tracking and detecting threatened and susceptible coral species. This paper proposes a new feature descriptor known as fractal adaptive weight synthesized-local directional pattern (FAWS-LDP) method to classify coral images using enhanced tree seed algorithm with extreme learning machine (ETSA-ELM) technique. The proposed feature descriptor (FAWS-LDP) inherits the advantage of both fractal pixel intensity information and local directional characteristics by indexing both feature vector values. Finally, the extracted features are imported to the extreme learning machine (ELM) network for classification. The ELM classifier is a single hidden layer feed-forward neural network with a faster learning speed and produces good generalization performance. The random selection of input weight and biases of the ELM classifier produces non-optimal or unnecessary input biases and weights to the network. Hence, to fine-tune the parameters of the ELM classifier, an enhanced tree seed algorithm (ETSA) is proposed. The proposed ETSA is a new learning technique to overcome the drawbacks like local optima and a lower coverage rate. The classification performance of ELM employing the ETSA optimizer is compared to the original TSA and other well-known metaheuristic algorithm (MHA) trainers, such as genetic algorithm (GA), particle swarm optimization (PSO), and artificial bee colony (ABC), utilizing model performance measures like specificity, sensitivity, and classification accuracy. The evaluation of coral classification datasets reveals that the proposed ETSA-ELM produces consistently superior performance to existing methods. Finally, the proposed feature descriptor technique is statistically analyzed using a non-parametric Friedman test to demonstrate the efficiency.

Integrating functional data analysis with case-based reasoning for hypertension prognosis and diagnosis based on real-world electronic health records

BackgroundHypertension is the fifth chronic disease causing death worldwide. The early prognosis and diagnosis are critical in the hypertension care process. Inspired by human philosophy, CBR is an empirical knowledge reasoning method for early detection and intervention of hypertension by only reusing electronic health records. However, the traditional similarity calculation method often ignores the internal characteristics and potential information of medical examination data.MethodsIn this paper, we first calculate the weights of input attributes by a random forest algorithm. Then, the risk value of hypertension from each medical examination can be evaluated according to the input data and the attribute weights. By fitting the risk values into a risk curve of hypertension, we calculate the similarity between different community residents, and obtain the most similar case according to the similarity. Finally, the diagnosis and treatment protocol of the new case can be given.ResultsThe experiment data comes from the medical examination of Tianqiao Community (Tongling City, Anhui Province, China) from 2012 to 2021. It contains 4143 community residents and 43,676 medical examination records. We first discuss the effect of the influence factor and the decay factor on similarity calculation. Then we evaluate the performance of the proposed FDA-CBR algorithm against the GRA-CBR algorithm and the CS-CBR algorithm. The experimental results demonstrate that the proposed algorithm is highly efficient and accurate.ConclusionsThe experiment results show that the proposed FDA-CBR algorithm can effectively describe the variation tendency of the risk value and always find the most similar case. The accuracy of FDA-CBR algorithm is higher than GRA-CBR algorithm and CS-CBR algorithm, increasing by 9.94 and 16.41%, respectively.

Intelligent quantification of natural gas pipeline defects using improved sparrow search algorithm and deep extreme learning machine

Accurate damage degree prediction is important to ensure the safety, stability, and economic operation of the natural gas pipeline in service, especially those in long-term service. In order to maintain the efficiency and safety of natural gas pipeline transportation, the intelligent diagnosis and evaluation technology of pipeline is very important. In this paper, The opposition-based learning strategy and adaptive T-distribution mutation operator are introduced to optimize the sparrow search algorithm (SSA),improve the search ability,convergence speed and accuracy of SSA algorithm. 12 classical benchmark functions are used to evaluate the performance of the improved algorithm. Experimental results demonstrate the feasibility and validity of ISSA compared with the original Sparrow search algorithm. Based on its excellent performance, ISSA is used to optimize the input layer weight and bias parameters of deep extreme learning machine (DELM). Therefore, a comprehensive ISSA-DELM network model is constructed for intelligent quantitative evaluation of natural gas pipeline defects. The results show that the model can effectively overcome the problem that the DELM effect is affected by the random input weight and random bias of each ELM-AE, and improve the quantitative prediction performance. This will facilitate the assessment of the integrity and safety status of natural gas pipelines.

Pfizer Stock Price Prediction Based on Extreme Learning Machine

Nowadays, an Extreme learning machine (ELM) is known to be a fast learning algorithm of single-hidden layer feedforward neural network (SLFNs), and overcomes the disadvantages of the classical learning algorithm in neural network methods multiple iterations, huge search space and a large number of calculations, only needs to set the appropriate numbers of hidden layer nodes, assigns the weight of input and deviation of hidden layers without iteration. Research shows that the stock market is a very complex nonlinear system, which requires artificial intelligence theory, statistics theory and economic theory to study the stock price forecast. In this paper, ELM is introduced in predicting the stock price of Pfizer company, and by comparing it with SVM and BP, we analyze its feasibility and advantage in stock price prediction. The experiment results show that ELM is of high accuracy of prediction and apparent advantages in parameter selection and learning speed．