Modified National Institute Of Standards And Technology Research Articles

Local Fourier features for handwriting digit images classification

Multiple choice questions (MCQ) are effective in normative assessment and offline testing is still relevant due to the lack of efficient mass infrastructures and maintenance. For the automatic correction of MCQ paper form and reporting of the grade, it is generally necessary to read and recognize a handwriting digit in a box. This paper focuses on local feature extraction in the frequency domain using Fourier transform. The pre-process begins with the extraction of the fields from the entity map, followed by the application of 2D fast Fourier transform (2DFFT) and the reduction of computed coefficients to obtain the corresponding final local characteristic in the representation. The experimental results of the Modified National Institute of Standards and Technology (MNIST) handwriting digits dataset show that the local characteristics extracted in the frequency domain used as input to a support vector machine (SVM) classifier are efficient in terms of 99.51% accuracy. The proposed system successfully helped in the reporting of all the marks for seven subjects in a class of 98 students during the automatic correction of the MCQ exam papers.

Convolution neural network hyperparameter optimization using modified particle swarm optimization

Based on the literature review, a convolutional neural network (CNN) is one of the deep learning techniques most often used for classification problems, especially image classification. Various approaches have been proposed to improve accuracy performance. In CNN architecture, parameter determination is very influential on accuracy performance. Particle swarm optimization (PSO) is a type of metaheuristic algorithm widely used for hyperparameter optimization. PSO convergence is faster than genetic algorithm (GA) and attracts many researchers for further studies such as genetic algorithms and ant colony. In PSO, determining the value of the weight parameter is very influential on accuracy. Therefore, this paper proposes CNN hyperparameter optimization using modified PSO with linearly decreasing randomized weight. The experiments use the modified National Institute of Standards and Technology (MNIST) dataset. The accuracy of the proposed method is superior, and the execution time is slower to random search. In epoch 1, epoch 3, and epoch 5, the proposed method is superior to baseline CNN, linearly decreasing weight PSO (LDWPSO), and RL-based optimization algorithm (ROA). Meanwhile, the accuracy performance of the proposed method is superior to previous studies, namely LeNet-1, LeNet-2, LeNet-3, PCANet-2, RANDNet-2, CAE1, CAE-2, and bee colony. Otherwise, lost to PSO-CNN, distributed PSO (DPSO), recurrent CNN, and CNN-PSO. However, the four methods have a complex architecture and wasteful execution time.

Noise-resilient single-pixel compressive sensing with single photon counting

The fast expansion of photon detection technology has fertilized the rapid growth of single-photon sensing and imaging techniques. While promising significant advantages over their classical counterparts, they suffer from ambient and quantum noises whose effects become more pronounced at low light levels, limiting the quality of the acquired signal. Here, we study how photon-counting noises degrade a single-pixel optical classifier via compressive sensing, and how its performance can be restored by using quantum parametric mode sorting. Using modified National Institute of Standards and Technology (MNIST) handwritten digits as an example, we examine the effects of detector dark counts and in-band background noises and demonstrate the effectiveness of mode filtering and upconversion detection in addressing those issues. We achieve 94% classification accuracy in the presence of 500 times stronger in-band noise than the signal received. Our results suggest a robust and efficient approach to single photon sensing in a practical environment, where sunlight, ambient, and multiscattering noises can easily dominate the weak signal.

A GAN-based anomaly detector using multi-feature fusion and selection

In numerous applications, abnormal samples are hard to collect, limiting the use of well-established supervised learning methods. GAN-based models which trained in an unsupervised and single feature set manner have been proposed by simultaneously considering the reconstruction error and the latent space deviation between normal samples and abnormal samples. However, the ability to capture the input distribution of each feature set is limited. Hence, we propose an unsupervised and multi-feature model, Wave-GANomaly, trained only on normal samples to learn the distribution of these normal samples. The model predicts whether a given sample is normal or not by its deviation from the distribution of normal samples. Wave-GANomaly fuses and selects from the wave-based features extracted by the WaveBlock module and the convolution-based features. The WaveBlock has proven to efficiently improve the performance on image classification, object detection, and segmentation tasks. As a result, Wave-GANomaly achieves the best average area under the curve (AUC) on the Canadian Institute for Advanced Research (CIFAR)-10 dataset (94.3%) and on the Modified National Institute of Standards and Technology (MNIST) dataset (91.0%) when compared to existing state-of-the-art anomaly detectors such as GANomaly, Skip-GANomaly, and the skip-attention generative adversarial network (SAGAN). We further verify our method by the self-curated real-world dataset, the result show that our method is better than GANomaly which only use single feature set for training the model.

Handwritten digit recognition using quantum convolution neural network

<span lang="EN-US">The recognition of handwritten digits holds a significant place in the field of information processing. Recognizing such characters accurately from images is a complex task because of the vast differences in people's writing styles. Furthermore, the presence of various image artifacts such as blurring, intensity variations, and noise adds to the complexity of this process. The existing algorithm, convolution neural network (CNN) is one of the prominent algorithms in deep learning to handle the above problems. But there is a difficulty in handling input data that differs significantly from the training data, leading to decreased accuracy and performance. In this work, a method is proposed to overcome the aforementioned limitations by incorporating a quantum convolutional neural network algorithm (QCNN). QCNN is capable of performing more complex operations than classical CNNs. It can achieve higher levels of accuracy than classical CNNs, especially when working with noisy or incomplete data. It has the potential to scale more efficiently and effectively than classical CNNs, making them better suited for large-scale applications. The effectiveness of the proposed model is demonstrated on the modified national institute of standards and technology (MNIST) dataset and achieved an average accuracy of 91.08%.</span>

Element Regulation and Dimensional Engineering Co-Optimization of Perovskite Memristors for Synaptic Plasticity Applications.

Capitalizing on rapid carrier migration characteristics and outstanding photoelectric conversion performance, halide perovskite memristors demonstrate an exceptional resistive switching performance. However, they have consistently faced constraints due to material stability issues. This study systematically employs elemental modulation and dimension engineering to effectively control perovskite memristors with different dimensions and A-site elements. Compared to pure 3D and 2D perovskites, the quasi-2D perovskite memristor, specifically BA0.15MA0.85PbI3, is identified as the optimal choice through observations of resistive switching (HRS current < 10-5 A, ON/OFF ratio > 103, endurance cycles > 1000, and retention time > 104 s) and synaptic plasticity characteristics. Subsequently, a comprehensive investigation into various synaptic plasticity aspects, including paired-pulse facilitation (PPF), spike-variability-dependent plasticity (SVDP), spike-rate-dependent plasticity (SRDP), and spike-timing-dependent plasticity (STDP), is conducted. Practical applications, such as memory-forgetting-memory and recognition of the Modified National Institute of Standards and Technology (MNIST) database handwritten data set (accuracy rate reaching 94.8%), are explored and successfully realized. This article provides good theoretical guidance for synaptic-like simulation in perovskite memristors.

Ferroelectric 2D SnS2 Analog Synaptic FET.

In this study, the development and characterization of 2D ferroelectric field-effect transistor (2D FeFET) devices are presented, utilizing nanoscale ferroelectric HfZrO2 (HZO) and 2D semiconductors. The fabricated device demonstrated multi-level data storage capabilities. It successfully emulated essential biological characteristics, including excitatory/inhibitory postsynaptic currents (EPSC/IPSC), Pair-Pulse Facilitation (PPF), and Spike-Timing Dependent Plasticity (STDP). Extensive endurance tests ensured robust stability (107 switching cycles, 105 s (extrapolated to 10 years)), excellent linearity, and high Gmax /Gmin ratio (>105 ), all of which are essential for realizing multi-level data states (>7-bit operation). Beyond mimicking synaptic functionalities, the device achieved a pattern recognition accuracy of ≈94% on the Modified National Institute of Standards and Technology (MNIST) handwritten dataset when incorporated into a neural network, demonstrating its potential as an effective component in neuromorphic systems. The successful implementation of the 2D FeFET device paves the way for the development of high-efficiency, ultralow-power neuromorphic hardware which is in sub-femtojoule (48 aJ/spike) and fast response (1 µs), which is 104 folds faster than human synapse (≈10ms). The results of the research underline the potential of nanoscale ferroelectric and 2D materials in building the next generation of artificial intelligence technologies.

Handwritten digit recognition based on deep learning techniques

The identification of handwritten digits in images recognition and machine learning is a prominent research area. In order to create a handwritten digit recognition model for this investigation, deep learning is introduced. The proposed approach integrates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and EfficientNetB0, three separate deep learning models. Specifically, the CNN model utilizes pooling layers and data augmentation techniques to enhance its classification ability, the RNN model takes advantage of its ability to process sequential data, and the EfficientNetB0 model benefits from a deeper and more complex network structure. These models are trained and evaluated using the Modified National Institute of Standards and Technology (MNIST) dataset. The experimental results demonstrate the efficacy of the proposed approach: the CNN model attains a remarkable accuracy of 98.9% on the test set, thereby showcasing its exceptional classification performance. Similarly, the RNN model achieves an accuracy of 96.7%, underscoring its suitability for analyzing sequential data. Furthermore, the EfficientNetB0 model attains an accuracy of 98.1%, thereby elucidating the benefits of the deeper network architecture. The models constructed in this study have significant real-world implications, such as improved object recognition systems, medical diagnostics, and autonomous driving. The EfficientNetB0 model produced an accuracy of 98.1% with its complex network architecture when applied to recognise handwritten digits.

SNNSim: Investigation and Optimization of Large‐Scale Analog Spiking Neural Networks Based on Flash Memory Devices

Spiking neural networks (SNNs) have emerged as a novel approach for reducing computational costs by mimicking the biologically plausible operations of neurons and synapses. In this article, large‐scale analog SNNs are investigated and optimized at the hardware‐level by using SNNSim, the novel simulator for SNNs that employ analog synaptic devices and integrate‐and‐fire (I&amp;F) neuron circuits. SNNSim is a reconfigurable simulator that accurately and very quickly models the behavior of the user‐defined device characteristics and returns key metrics such as area, accuracy, latency, and power consumption as output. Notably, SNNSim exhibits exceptional efficiency, as it can process the entire 10 000 Modified National Institute of Standards and Technology (MNIST) test dataset in a few seconds, whereas SPICE simulations require hours to simulate a single MNIST test data. Using SNNSim, the conversion of artificial neural networks (ANNs) to SNNs is simulated and the performance of the large‐scale analog SNNs is optimized. The results enable the design of accurate, high‐speed, and low‐power operation of large‐scale SNNs. SNNSim code is now available at https://github.com/SMDLGITHUB/SNNSim.

Realization of future neuro-biological architecture in power efficient memristors of Fe3O4/WS2 hybrid nanocomposites

The future generation of digital technology will heavily rely on power efficient non-volatile resistive memory systems as a potential alternative to flash memory due to its limitations in scalability and endurance. To attain the commercial benchmark, memristors have still lacked performance. This study reports a novel and cost-effective solution processable method for growing surface-modified hybrid nanocomposites (Nc) on a large scale, as an active layer. The solution-processed synthesis approach used for Ag/Fe50W50/Pt hybrid nanocomposite memristor device results in the formation of heterophase grain boundaries, which create residual filaments along these boundaries. The device Fe3O4-WS2(Nc) shows excellent performance, having ultra-low energy consumption (0.1fJ), high reproducibility (10 devices), scalability, excellent endurance (106), and excellent environment stability. Density functional theory (DFT) simulations reveal that structural symmetry distortion and interfacial interaction of hybrid nanocomposite at the interface plays a vital role in the switching mechanism. As high-performance electronic synapses, the optimal pulse scheme enables a steady interaction of short- and long-term plasticity principles, such as spike -time dependent plasticity (STDP) and pulse pair facilitation (PPF), essential for learning and neuromorphic computing analogous to human brain. Moreover, by using Modified National Institute of Standards and Technology (MINST), the memristor device attained a high learning accuracy of 95.4% under convolution neural network (CNN) simulations. The present study revealed that the performance of hybrid-nanocomposite memristors could lead to efficient future neuromorphic architecture.

Spin orbit magnetic random access memory based binary CNN in-memory accelerator (BIMA) with sense amplifier

The research tends to suggest a spin-orbit torque magnetic random access memory (SOT-MRAM)-based Binary CNN In-Memory Accelerator (BIMA) to minimize power utilization and suggests an In-Memory Computing (IMC) for AdderNet-based BIMA to further enhance performance by fully utilizing the benefits of IMC as well as a low current consumption configuration employing SOT-MRAM. And recommended an IMC-friendly computation pipeline for AdderNet convolution at the algorithm level. Additionally, the suggested sense amplifier is not only capable of the addition operation but also typical Boolean operations including subtraction etc. The architecture suggested in this research consumes less power than its spin-orbit torque (STT) MRAM and resistive random access memory (ReRAM)-based counterparts in the Modified National Institute of Standards and Technology (MNIST) data set, according to simulation results. Based to evaluation outcomes, the pre-sented strategy outperforms the in-memory accelerator in terms of speedup and energy efficiency by 17.13× and 18.20×, respectively.

A carbon conductive filament-induced robust resistance switching behavior for brain-inspired computing.

Memristors have revolutionized the path forward for brain-inspired computing. However, the instability of the nucleation process of conductive filaments based on active metal electrodes leads to the discrete distribution of switching parameters, which hinders the realization of high-performance and low-power devices for neuromorphic computing. In response, a carbon conductive filament-induced robust memristor is demonstrated with variation coefficients as low as 3.9%/-1.18%, a threshold power as low as 10-9 W, and 3 × 106 s retention and 107 cycle endurance behaviors can be maintained. The recognition accuracy for Modified National Institute of Standards and Technology (MNIST) handwriting is as high as 96.87%, attributed to the high linearity of the iterative updating of synaptic weights. The demodulation and storage functions of the American Standard Code for Information Interchange (ASCII) are demonstrated by programmable pulse modulation. Notably, the transmission electron microscopy (TEM) images allow the observation of carbon conductive filament paths formed in the low resistance state. First-principles calculations analyze the energetics of defects involved in the diffusion of carbon atoms into MoTe2 films. This work presents a novel guideline for studying memristor-based neuromorphic computing.

Hierarchical Spiking-Based Model for Efficient Image Classification With Enhanced Feature Extraction and Encoding.

Thanks to their event-driven nature, spiking neural networks (SNNs) are surmised to be great computation-efficient models. The spiking neurons encode beneficial temporal facts and possess excessive anti-noise properties. However, the high-quality encoding of spatio-temporal complexity and also its training optimization of SNNs are restricted by means of the contemporary problem, this article proposes a novel hierarchical event-driven visual device to explore how information transmits and signifies in the retina the usage of biologically manageable mechanisms. This cognitive model is an augmented spiking-based framework consisting of the function learning capacity of convolutional neural networks (CNNs) with the cognition capability of SNNs. Furthermore, this visual device is modeled in a biological realism way with unsupervised learning rules and advanced spike firing rate encoding methods. We train and test them on some image datasets (Modified National Institute of Standards and Technology (MNIST), Canadian Institute for Advanced Research (CIFAR)10, and its noisy versions) to show that our mannequin can process greater vital data than present cognitive models. This article also proposes a novel quantization approach to make the proposed spiking-based model more efficient for neuromorphic hardware implementation. The outcomes show this joint CNN-SNN model can reap excessive focus accuracy and get more effective generalization ability.

Adapted MLP-Mixer network based on crossbar arrays of fast and multilevel switching (Co-Fe-B)x(LiNbO3)100-x nanocomposite memristors.

MLP-Mixer based on multilayer perceptrons (MLPs) is a novel architecture of a neuromorphic computing system (NCS) introduced for image classification tasks without convolutional layers. Its software realization demonstrates high classification accuracy, although the number of trainable weights is relatively low. One more promising way of improving the NCS performance, especially in terms of power consumption, is its hardware realization using memristors. Therefore, in this work, we proposed an NCS with an adapted MLP-Mixer architecture and memristive weights. For this purpose, we used a passive crossbar array of (Co-Fe-B)x(LiNbO3)100-x memristors. Firstly, we studied the characteristics of such memristors, including their minimal resistive switching time, which was extrapolated to be in the picosecond range. Secondly, we created a fully hardware NCS with memristive weights that are capable of classification of simple 4-bit vectors. The system was shown to be robust to noise introduction in the input patterns. Finally, we used experimental memristive characteristics to simulate an adapted MLP-Mixer architecture that demonstrated a classification accuracy of (94.7 ± 0.3)% on the Modified National Institute of Standards and Technology (MNIST) dataset. The obtained results are the first steps toward the realization of memristive NCS with a promising MLP-Mixer architecture.

Efficient approximate multipliers utilizing compact and low-power compressors for error-resilient applications

Approximate computing is one of the promising techniques in error-resilient applications to overcome high-density integration challenges, such as energy consumption and performance. Multipliers constitute a significant portion of computer arithmetic units, leading to considerable energy and time consumption. In this paper, we propose low-power and compact approximate compressors for composing approximate Dadda multiplier structures, including compressors, half adders, and full adders, which utilize three-phase partial product compression: truncated, approximation, and exact columns. In approximate columns, we consider approximate compressors derived from the truth table of the exact 4:2 compressor and simplified K-map entries based on the probability of each combination of inputs. An error-correcting module (ECM) is designed to distinguish specific cases and reduce the error metrics. All circuits were simulated using ModelSim and then synthesized using Design Compiler with the 15 nm FinFET technology. When compared to state-of-the-art works, our multipliers exhibit approximately 30%, 43%, and 10% reductions in power, area, and delay, respectively. To evaluate their functionality, we conducted image multiplication and implemented a simple multi-layer perceptron (MLP) neural network using the modified National Institute of Standards and Technology (MNIST) dataset in MATLAB with 0.998 mean structural similarity index metric (MSSIM), 51 dB peak-signal noise ratio (PSNR), and 95% classification accuracy.

Enhancing functional efficiency in information-extreme machine learning with logistic regression ensembles

The subject matter of the article is the application of supervised machine learning for the task of object class recognition. The goal is enhancing functional efficiency in information-extreme technology (IET) for object class recognition. The tasks to be solved are: to analyse possible ways of increasing the functional efficiency IET approach; implement an ensemble of models that include logistic regression for prioritizing recognition features and an IEI learning algorithm; compare the functional efficiency of the resulting ensemble of models on well-known dataset with classic approach and results of other researchers. The methods: The method is developed within the framework of the functional approach to modelling natural intelligence applied to the problem of object classification. The following results were obtained: The study tries to augment existing IET to support feature prioritization as part of the object class recognition algorithm. The classical information-extreme algorithm treats all input features equivalently important in forming the decisive rule. As a result, the object features with strong correlation are not prioritized by the algorithm's decisive mechanism – resulting in decreasing functional efficiency in exam mode. The proposed approach is solving this problem by applying a two-stage approach. In the first stage the multiclass logistic regression applied to the input training features vectors of objects to be classified – formed the normalized training matrix. To prevent overfitting of the logistic regression, a model the L2(ridge) regularization method was used. On the second stage, the information-extreme method as input takes the result of the first stage. The geometrical parameters of class containers and the control tolerances on the recognition features were considered as the optimization parameters. Conclusions. The proposed approach increases MNIST (Modified National Institute of Standards and Technology) dataset classification accuracy compared with the classic information-extreme method by 26,44%. The proposed approach has a 3.77% lower accuracy compared to neural-like approaches but uses fewer resources in the training phase and allows retraining the model, as well as expanding the dictionary of recognition classes without model retraining.

Integrated In-Memory Sensor and Computing of Artificial Vision Based on Full-vdW Optoelectronic Ferroelectric Field-Effect Transistor.

The development and application of artificial intelligence have led to the exploitation of low-power and compact intelligent information-processing systems integrated with sensing, memory, and neuromorphic computing functions. The 2D van der Waals (vdW) materials with abundant reservoirs for arbitrary stacking based on functions and enabling continued device downscaling offer an attractive alternative for continuously promoting artificial intelligence. In this study, full 2D SnS2 /h-BN/CuInP2 S6 (CIPS)-based ferroelectric field-effect transistors (Fe-FETs) and utilized light-induced ferroelectric polarization reversal to achieve excellent memory properties and multi-functional sensing-memory-computing vision simulations are designed. The device exhibits a high on/off current ratio of over 105 , long retention time (>104 s), stable cyclic endurance (>350 cycles), and 128 multilevel current states (7-bit). In addition, fundamental synaptic plasticity characteristics are emulated including paired-pulse facilitation (PPF), short-term plasticity (STP), long-term plasticity (LTP), long-term potentiation, and long-term depression. A ferroelectric optoelectronic reservoir computing system for the Modified National Institute of Standards and Technology (MNIST) handwritten digital recognition achieved a high accuracy of 93.62%. Furthermore, retina-like light adaptation and Pavlovian conditioning are successfully mimicked. These results provide a strategy for developing a multilevel memory and novel neuromorphic vision systems with integrated sensing-memory-processing.

Emulation of Pavlovian conditioning and pattern recognition through fully connected neural networks using Holmium oxide (Ho2O3) based synaptic RRAM device.

In this manuscript, we report on the paramagnetic Ho2O3 -based synaptic resistive random-access memory (RRAM) device for the implementation of neuronal functionalities such as long-term potentiation (LTP), long-term depression (LTD) and spike timing dependent plasticity (STDP) respectively. The plasticity of the artificial synapse is also studied by varying pulse amplitude, pulse width, and pulse interval. In addition, we could classify handwritten Modified National Institute of Standards and Technology (MNIST) data set using a fully connected neural network (FCN). The device-based FCN records a high classification accuracy of 93.47% which is comparable to the software-based test accuracy of 97.97%. This indicates the highly optimized behavior of our synaptic device for hardware neuromorphic applications. Successful emulation of Pavlovian classical conditioning for associative learning of the biological brain is achieved. We believe that the present device consists the potential to utilize in neuromorphic applications.

Kernel Mapping Methods of Convolutional Neural Network in 3D NAND Flash Architecture

A flash memory is a non-volatile memory that has a large memory window, high cell density, and reliable switching characteristics and can be used as a synaptic device in a neuromorphic system based on 3D NAND flash architecture. We fabricated a TiN/Al2O3/Si3N4/SiO2/Si stack-based Flash memory device with a polysilicon channel. The input/output signals and output values are binarized for accurate vector-matrix multiplication operations in the hardware. In addition, we propose two kernel mapping methods for convolutional neural networks (CNN) in the neuromorphic system. The VMM operations of two mapping schemes are verified through SPICE simulation. Finally, the off-chip learning in the CNN structure is performed using the Modified National Institute of Standards and Technology (MNIST) dataset. We compared the two schemes in terms of various parameters and determined the advantages and disadvantages of each.

Salient Arithmetic Data Extraction from Brain Activity via an Improved Deep Network

Interpretation of neural activity in response to stimulations received from the surrounding environment is necessary to realize automatic brain decoding. Analyzing the brain recordings corresponding to visual stimulation helps to infer the effects of perception occurring by vision on brain activity. In this paper, the impact of arithmetic concepts on vision-related brain records has been considered and an efficient convolutional neural network-based generative adversarial network (CNN-GAN) is proposed to map the electroencephalogram (EEG) to salient parts of the image stimuli. The first part of the proposed network consists of depth-wise one-dimensional convolution layers to classify the brain signals into 10 different categories according to Modified National Institute of Standards and Technology (MNIST) image digits. The output of the CNN part is fed forward to a fine-tuned GAN in the proposed model. The performance of the proposed CNN part is evaluated via the visually provoked 14-channel MindBigData recorded by David Vivancos, corresponding to images of 10 digits. An average accuracy of 95.4% is obtained for the CNN part for classification. The performance of the proposed CNN-GAN is evaluated based on saliency metrics of SSIM and CC equal to 92.9% and 97.28%, respectively. Furthermore, the EEG-based reconstruction of MNIST digits is accomplished by transferring and tuning the improved CNN-GAN’s trained weights.