Pure voltage-driven spintronic neuron based on stochastic magnetization switching behaviour

2021 ◽  
Author(s):  
Jia-Hui Yuan ◽  
Ya-Bo Chen ◽  
Shu-qing Dou ◽  
Bo Wei ◽  
Huanqing Cui ◽  
...  
Keyword(s):  
Neural Network ◽  
Energy Efficient ◽  
Pulse Width ◽  
Recognition Accuracy ◽  
High Reliability ◽  
Magnetization Vector ◽  
Activation Function ◽  
Low Power Consumption ◽  
Magnetization Switching ◽  
Artificial Neuron

Abstract Voltage-driven stochastic magnetization switching in a nanomagnet has attracted more attention recently with its superiority in achieving energy-efficient artificial neuron. Here, a novel pure voltage-driven scheme with ~27.66 aJ energy dissipation is proposed, which could rotate magnetization vector randomly using only a pair of electrodes covered on the multiferroic nanomagnet. Results show that the probability of 180° magnetization switching is examined as a sigmoid-like function of the voltage pulse width and magnitude, which can be utilized as the activation function of designed neuron. Considering the size errors of designed neuron in fabrication, it’s found that reasonable thickness and width variations cause little effect on recognition accuracy for MNIST hand-written dataset. In other words, the designed pure voltage-driven spintronic neuron could tolerate size errors. These results open a new way toward the realization of artificial neural network with low power consumption and high reliability.

scholarly journals An energy efficient time-mode digit classification neural network implementation

2019 ◽  
Vol 378 (2164) ◽  
pp. 20190163
Author(s):  
O. C. Akgun ◽  
J. Mei
Keyword(s):  
Neural Network ◽  
Energy Efficient ◽  
Supply Voltage ◽  
Single Layer ◽  
Activation Function ◽  
Monostable Multivibrator ◽  
Pulse Generators ◽  
Autonomous Computing ◽  
Handwritten Digit ◽  
Artificial Neural Network Ann

This paper presents the design of an ultra-low energy neural network that uses time-mode signal processing). Handwritten digit classification using a single-layer artificial neural network (ANN) with a Softmin-based activation function is described as an implementation example. To realize time-mode operation, the presented design makes use of monostable multivibrator-based multiplying analogue-to-time converters, fixed-width pulse generators and basic digital gates. The time-mode digit classification ANN was designed in a standard CMOS 0.18 μm IC process and operates from a supply voltage of 0.6 V. The system operates on the MNIST database of handwritten digits with quantized neuron weights and has a classification accuracy of 88%, which is typical for single-layer ANNs, while dissipating 65.74 pJ per classification with a speed of 2.37 k classifications per second. This article is part of the theme issue ‘Harmonizing energy-autonomous computing and intelligence’.

scholarly journals Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

2021 ◽  
Vol 15 ◽  
Author(s):  
Lixing Huang ◽  
Jietao Diao ◽  
Hongshan Nie ◽  
Wei Wang ◽  
Zhiwei Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Precision ◽  
Network Architecture ◽  
Large Scale ◽  
Network Performance ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Data Set ◽  
Neuron Activation

The memristor-based convolutional neural network (CNN) gives full play to the advantages of memristive devices, such as low power consumption, high integration density, and strong network recognition capability. Consequently, it is very suitable for building a wearable embedded application system and has broad application prospects in image classification, speech recognition, and other fields. However, limited by the manufacturing process of memristive devices, high-precision weight devices are currently difficult to be applied in large-scale. In the same time, high-precision neuron activation function also further increases the complexity of network hardware implementation. In response to this, this paper proposes a configurable full-binary convolutional neural network (CFB-CNN) architecture, whose inputs, weights, and neurons are all binary values. The neurons are proportionally configured to two modes for different non-ideal situations. The architecture performance is verified based on the MNIST data set, and the influence of device yield and resistance fluctuations under different neuron configurations on network performance is also analyzed. The results show that the recognition accuracy of the 2-layer network is about 98.2%. When the yield rate is about 64% and the hidden neuron mode is configured as −1 and +1, namely ±1 MD, the CFB-CNN architecture achieves about 91.28% recognition accuracy. Whereas the resistance variation is about 26% and the hidden neuron mode configuration is 0 and 1, namely 01 MD, the CFB-CNN architecture gains about 93.43% recognition accuracy. Furthermore, memristors have been demonstrated as one of the most promising devices in neuromorphic computing for its synaptic plasticity. Therefore, the CFB-CNN architecture based on memristor is SNN-compatible, which is verified using the number of pulses to encode pixel values in this paper.

Methods and means for real-time object recognition accuracy increase in video images on ios mobile platform

2021 ◽  
Vol 3 (1) ◽  
pp. 80-88
Author(s):  
D Kushnir ◽  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Frame Rate ◽  
Mobile Platform ◽  
Additional Layer ◽  
The Neural Network ◽  
Analytical Review ◽  
Accuracy Increase

As a result of the analytical review, it was established that the family of Yolo models is a promising area of search and recognition of objects. However, existing implementations do not support the ability to run the model on the iOS platform. To achieve these goals, a comprehensive scalable conversion system has been developed to improve the recognition accuracy of arbitrary models based on the Docker system. The method of improvement is to add a layer with the Mish activation function to the original model. The method of conversion is to quickly convert any Yolo model to CoreML format. As part of the study of these techniques, a model of the neural network Yolov4_TCAR was created. Additionally, a method of accelerating the load on the CPU using an additional layer of neural network with the function of activating Mish in Swift for the iOS mobile platform was added. As a result, the effectiveness of the Mish activation function, the CPU load of the mobile device, the amount of RAM used, and the frame rate when using the improved original Yolov4-TCAR model were studied. The results of the research confirmed the functioning of the algorithm for conversion and accuracy increase of the neural network model in real-time.

A Multi-Feature Convolution Neural Network for Automatic Flower Recognition

2021 ◽  
pp. 2150281
Author(s):  
Juan Ran ◽  
Yu Shi ◽  
Jinhao Yu ◽  
Delong Li
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Local Binary Pattern ◽  
Recognition Accuracy ◽  
Texture Features ◽  
Activation Function ◽  
Multiple Features ◽  
Color Features ◽  
Definition Of ◽  
Texture Extraction

This paper discusses how to efficiently recognize flowers based on a convolutional neural network (CNN) using multiple features. Our proposed work consists of three phases including segmentation by Otsu thresholding with particle swarm optimization algorithms, feature extraction of color, shape, texture and recognition with the LeNet-5 neural network. In the feature extraction, an improved H component with the definition of WGB value is applied to extract the color feature, and a new algorithm based on local binary pattern (LBP) is proposed to enhance the accuracy of texture extraction. Besides this, we replace ReLU with Mish as activation function in the network design, and therefore increase the accuracy by 8% accuracy according to our comparison. The Oxford-102 and Oxford-17 datasets are adopted for benchmarking. The experimental results show that the combination of color features and texture features generates the highest recognition accuracy as 92.56% on Oxford-102 and 93% on Oxford-17.

scholarly journals An Energy-Efficient Time-Domain Analog CMOS BinaryConnect Neural Network Processor Based on a Pulse-Width Modulation Approach

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 2644-2654
Author(s):  
Masatoshi Yamaguchi ◽  
Goki Iwamoto ◽  
Yuta Nishimura ◽  
Hakaru Tamukoh ◽  
Takashi Morie
Keyword(s):  
Neural Network ◽  
Time Domain ◽  
Energy Efficient ◽  
Pulse Width ◽  
Pulse Width Modulation ◽  
Network Processor ◽  
Analog Cmos

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

scholarly journals Prediction of Stress in Power Transformer Winding Conductors Using Artificial Neural Networks: Hyperparameter Analysis

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4242
Author(s):  
Fausto Valencia ◽  
Hugo Arcos ◽  
Franklin Quilumba
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Power Transformer ◽  
Network Models ◽  
Activation Function ◽  
Neural Network Models ◽  
Transformer Winding ◽  
Artificial Neural ◽  
Femm Software

The purpose of this research is the evaluation of artificial neural network models in the prediction of stresses in a 400 MVA power transformer winding conductor caused by the circulation of fault currents. The models were compared considering the training, validation, and test data errors’ behavior. Different combinations of hyperparameters were analyzed based on the variation of architectures, optimizers, and activation functions. The data for the process was created from finite element simulations performed in the FEMM software. The design of the Artificial Neural Network was performed using the Keras framework. As a result, a model with one hidden layer was the best suited architecture for the problem at hand, with the optimizer Adam and the activation function ReLU. The final Artificial Neural Network model predictions were compared with the Finite Element Method results, showing good agreement but with a much shorter solution time.

scholarly journals Graphene-based 3D XNOR-VRRAM with ternary precision for neuromorphic computing

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Batyrbek Alimkhanuly ◽  
Joon Sohn ◽  
Ik-Joon Chang ◽  
Seunghyun Lee
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Recognition Accuracy ◽  
Material Selection ◽  
Weighted Sum ◽  
Device Design ◽  
Key Factors ◽  
Neuromorphic Computing ◽  
Device Scaling ◽  
The Impact

AbstractRecent studies on neural network quantization have demonstrated a beneficial compromise between accuracy, computation rate, and architecture size. Implementing a 3D Vertical RRAM (VRRAM) array accompanied by device scaling may further improve such networks’ density and energy consumption. Individual device design, optimized interconnects, and careful material selection are key factors determining the overall computation performance. In this work, the impact of replacing conventional devices with microfabricated, graphene-based VRRAM is investigated for circuit and algorithmic levels. By exploiting a sub-nm thin 2D material, the VRRAM array demonstrates an improved read/write margins and read inaccuracy level for the weighted-sum procedure. Moreover, energy consumption is significantly reduced in array programming operations. Finally, an XNOR logic-inspired architecture designed to integrate 1-bit ternary precision synaptic weights into graphene-based VRRAM is introduced. Simulations on VRRAM with metal and graphene word-planes demonstrate 83.5 and 94.1% recognition accuracy, respectively, denoting the importance of material innovation in neuromorphic computing.

Sign in / Sign up

Export Citation Format

Share Document