scholarly journals Nanoscale neural network using non-linear spin-wave interference

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ádám Papp ◽  
Wolfgang Porod ◽  
Gyorgy Csaba
Keyword(s):  
Neural Network ◽  
Spin Wave ◽  
Spin Waves ◽  
Field Pattern ◽  
Small Scale ◽  
Learning Framework ◽  
Wave Interference ◽  
The Neural Network ◽  
Neural Network Hardware ◽  
Signal Routing

AbstractWe demonstrate the design of a neural network hardware, where all neuromorphic computing functions, including signal routing and nonlinear activation are performed by spin-wave propagation and interference. Weights and interconnections of the network are realized by a magnetic-field pattern that is applied on the spin-wave propagating substrate and scatters the spin waves. The interference of the scattered waves creates a mapping between the wave sources and detectors. Training the neural network is equivalent to finding the field pattern that realizes the desired input-output mapping. A custom-built micromagnetic solver, based on the Pytorch machine learning framework, is used to inverse-design the scatterer. We show that the behavior of spin waves transitions from linear to nonlinear interference at high intensities and that its computational power greatly increases in the nonlinear regime. We envision small-scale, compact and low-power neural networks that perform their entire function in the spin-wave domain.

scholarly journals Towards Better Forecasting by Fusing Near and Distant Future Visions

2020 ◽  
Vol 34 (04) ◽  
pp. 3593-3600
Author(s):  
Jiezhu Cheng ◽  
Kaizhu Huang ◽  
Zibin Zheng
Keyword(s):  
Neural Network ◽  
Multivariate Time Series ◽  
Predictive Performance ◽  
Distant Future ◽  
Forecasting Accuracy ◽  
Learning Framework ◽  
The Neural Network ◽  
Multi Level ◽  
Real World Datasets ◽  
Future Visions

Multivariate time series forecasting is an important yet challenging problem in machine learning. Most existing approaches only forecast the series value of one future moment, ignoring the interactions between predictions of future moments with different temporal distance. Such a deficiency probably prevents the model from getting enough information about the future, thus limiting the forecasting accuracy. To address this problem, we propose Multi-Level Construal Neural Network (MLCNN), a novel multi-task deep learning framework. Inspired by the Construal Level Theory of psychology, this model aims to improve the predictive performance by fusing forecasting information (i.e., future visions) of different future time. We first use the Convolution Neural Network to extract multi-level abstract representations of the raw data for near and distant future predictions. We then model the interplay between multiple predictive tasks and fuse their future visions through a modified Encoder-Decoder architecture. Finally, we combine traditional Autoregression model with the neural network to solve the scale insensitive problem. Experiments on three real-world datasets show that our method achieves statistically significant improvements compared to the most state-of-the-art baseline methods, with average 4.59% reduction on RMSE metric and average 6.87% reduction on MAE metric.

scholarly journals Neural Network Based Hurdle Avoidance System for Smart Vehicles

2019 ◽  
Vol 8 (04) ◽  
pp. 01-07
Author(s):  
Dr. B. Maruthi Shankar
Keyword(s):  
Neural Network ◽  
Small Scale ◽  
Direct Estimate ◽  
Feed Forward ◽  
Smart Vehicles ◽  
Ir Sensor ◽  
The Neural Network ◽  
Feed Forward Network ◽  
Positive Direct ◽  
Matlab Programming

The structure of a self-ruling vehicle dependent on neural sophisticated network for route in obscure condition is proposed. The vehicle is equipped with an IR sensor for obstacle separation estimation, a GPS collector for goal data and heading position, L298 H-connect for driving the engines which runs the wheels; all interfaced to a controller unit. The smaller scale controller forms the data gained from the sensor and GPS to produce robot movement through neural based network. The neural network running inside the small scale controller is a multi-layer feed-forward network with back-engendering blunder calculation. The network is prepared disconnected with tangent-sigmoid and positive direct estimate as enactment work for neurons and is executed progressively with piecewise straight guess of tangent-sigmoid capacity. The programming of the miniaturized scale controller is finished by PIC C Compiler and the neural network is actualized utilizing MATLAB programming. Results have shown that up to twenty neurons can be actualized in shrouded layer with this method. The vehicle is tried with differing goal places in open air situations containing fixed as well as moving obstructions and is found to arrive at the set targets effectively and its yield exactness is about equivalent to that of the normal precision.

scholarly journals Fast automated detection of COVID-19 from medical images using convolutional neural networks

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Shuang Liang ◽  
Huixiang Liu ◽  
Yu Gu ◽  
Xiuhua Guo ◽  
Hongjun Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Medical Images ◽  
Clinical Indicators ◽  
Specimen Handling ◽  
Learning Framework ◽  
Computed Tomography Images ◽  
Classification Framework ◽  
Global Pandemic ◽  
The Neural Network ◽  
Diagnosis Method

AbstractCoronavirus disease 2019 (COVID-19) is a global pandemic posing significant health risks. The diagnostic test sensitivity of COVID-19 is limited due to irregularities in specimen handling. We propose a deep learning framework that identifies COVID-19 from medical images as an auxiliary testing method to improve diagnostic sensitivity. We use pseudo-coloring methods and a platform for annotating X-ray and computed tomography images to train the convolutional neural network, which achieves a performance similar to that of experts and provides high scores for multiple statistical indices (F1 scores > 96.72% (0.9307, 0.9890) and specificity >99.33% (0.9792, 1.0000)). Heatmaps are used to visualize the salient features extracted by the neural network. The neural network-based regression provides strong correlations between the lesion areas in the images and five clinical indicators, resulting in high accuracy of the classification framework. The proposed method represents a potential computer-aided diagnosis method for COVID-19 in clinical practice.

scholarly journals Inferring depth-dependent plasma motions from surface observations using the DeepVel neural network

2020 ◽  
Author(s):  
Benoit Tremblay ◽  
Jean-François Cossette ◽  
Maria D. Kazachenko ◽  
Paul Charbonneau ◽  
Alain Patrick Vincent
Keyword(s):  
Neural Network ◽  
Data Assimilation ◽  
Numerical Simulations ◽  
Active Regions ◽  
Transverse Component ◽  
Small Scale ◽  
Solar Photosphere ◽  
Quiet Sun ◽  
The Neural Network ◽  
Spatial Coverage

Coverage of plasma motions is limited to the line-of-sight component at the Sun's surface. Multiple tracking and inversion methods were developed to infer the transverse motions from observational data. Recently, the DeepVel neural network was trained with computations performed by numerical simulations of the solar photosphere to recover the missing transverse component at surface and at two additional optical depths simultaneously from the surface white light intensity in the Quiet Sun. We argue that deep learning could provide additional spatial coverage to existing observations in the form of depth-dependent synthetic observations, i.e. estimates generated through the emulation of numerical simulations. We trained different versions of DeepVel using slices from numerical simulations of both the Quiet Sun and Active Region at various optical and geometrical depths in the solar atmosphere, photosphere and upper convection zone to establish the upper and lower limits at which the neural network can generate reliable synthetic observations of plasma motions from surface intensitygrams. Flow fields inferred in the photosphere and low chromosphere $\tau \in [0.1, 1)$ are comparable to inversions performed at the surface ($\tau \approx 1$) and are deemed to be suitable for use as synthetic observations in data assimilation processes and data-driven simulations. This upper limit extends closer to the transition region ($\tau \approx 0.01$) in the Quiet Sun, but not for Active Regions. Subsurface flows inferred from surface intensitygrams fail to capture the small-scale features of turbulent convective motions as depth crosses a few hundred kilometers. We suggest that these reconstructions could be used as first estimates of a model's velocity vector in data assimilation processes to nowcast and forecast short term solar activity and space weather.

scholarly journals Early Mass Diagnosis of Fusarium Wilt in Banana Cultivations using an E-Nose Integrated Autonomous Rover System

2017 ◽  
Vol 5 (2) ◽  
pp. 261-266 ◽  
Author(s):  
M. Sanjay ◽  
B. Kalpana
Keyword(s):  
Neural Network ◽  
Fusarium Wilt ◽  
Infected Plant ◽  
Disease Outbreaks ◽  
Training Model ◽  
Early Warning Systems ◽  
Small Scale ◽  
The Neural Network ◽  
Similar Disease ◽  
And Control

Nucleic acid based diagnostics are the standard means for diagnosis of infected plant material. However, these methods are expensive and time-consuming, but they are accurate. On the contrary, disease prediction methods based on Volatile organic compound (VOC) emission from plants are less accurate but, allow for screening of large volumes of samples. This work reports the methodology for development of an inexpensive electronic nose for implementation as early warning systems intended to prevent plant disease outbreaks using VOC pattern analysis. It is proven that plants emit VOCs in response to pathogenic attacks. In this project, efforts were made to register the pattern of VOCs released by the diseased plants. The disease taken for this purpose was Fusarium wilt disease of banana. The E-Nose was successfully fabricated using five MOS sensors connected to a microcontroller, which along with a microSD card module was able to store the acquired VOC data. The VOC data analysis was done in MS-Excel, using NeuroXL Predictor, a neural networking add-in. A small scale banana field containing 35 plants, divided into disease, test and control groups, was established. The disease and test sets were subjected to similar disease induction protocols and VOC data was collected over a period of 40 days. NeuroXL Predictor was trained to recognize odours corresponding to diseases by feeding the neural network with the disease set VOC data. Finally, the training model was validated by providing the test set VOC data to the neural network and the results were found to be accurate. Efforts were made to automate the VOC data acquisition from the plants, as it will be impractical to carry around, a device, through several hectares of plantation. Therefore, a simple autonomous rover was fabricated using DC motors connected to a microcontroller. A DC motor placed on top was used to move the E-nose towards the plants in left and right of the rover. The microcontroller was programmed to stop, move forward and turn the E-nose towards left or right as per the measurements of the field.Int. J. Appl. Sci. Biotechnol. Vol 5(2): 261-266

Development of Deep Learning Framework for Mathematical Morphology

2019 ◽  
Vol 33 (06) ◽  
pp. 1954024 ◽  
Author(s):  
Frank Y. Shih ◽  
Yucong Shen ◽  
Xin Zhong
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Mathematical Morphology ◽  
Experimental Results ◽  
Morphological Operations ◽  
Learning Framework ◽  
Structuring Element ◽  
The Neural Network ◽  
Object Features

Mathematical morphology has been applied as a collection of nonlinear operations related to object features in images. In this paper, we present morphological layers in deep learning framework, namely MorphNet, to perform atomic morphological operations, such as dilation and erosion. For propagation of losses through the proposed deep learning framework, we approximate the dilation and erosion operations by differential and smooth multivariable functions of the softmax function, and therefore enable the neural network to be optimized. The proposed operations are analyzed by the derivative of approximation functions in the deep learning framework. Experimental results show that the output structuring element of a morphological neuron and the target structuring element are matched to confirm the efficiency and correctness of the proposed framework.

scholarly journals Bearing Defect Classification Algorithm Based on Autoencoder Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-9 ◽  
Author(s):  
Manhuai Lu ◽  
Yuanxiang Mou
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Feature Selection ◽  
Defect Detection ◽  
Classification Accuracy ◽  
Large Scale ◽  
Small Scale ◽  
Defect Classification ◽  
The Neural Network ◽  
Bearing Defect

The postproduction defect classification and detection of bearings still relies on manual detection, which is time-consuming and tedious. To address this, we propose a bearing defect classification network based on an autoencoder to enhance the efficiency and accuracy of bearing defect detection. An improved autoencoder is used to reduce dimension feature extraction and reduce large-scale images to small-scale images through encoder dimensional reduction. Defect classification is completed by feeding the extracted features into a convolutional classification network. Comparative experiments show that the neural network can effectively complete feature selection and substantially improve classification accuracy while avoiding the laborious algorithm of the conventional method.

scholarly journals Extracting automata from neural networks using active learning

2021 ◽  
Vol 7 ◽  
pp. e436
Author(s):  
Zhiwu Xu ◽  
Cheng Wen ◽  
Shengchao Qin ◽  
Mengda He
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Active Learning ◽  
Block Size ◽  
Learning Framework ◽  
Passive Learning ◽  
The Neural Network ◽  
Equivalence Queries ◽  
Neural Network Classifiers

Deep learning is one of the most advanced forms of machine learning. Most modern deep learning models are based on an artificial neural network, and benchmarking studies reveal that neural networks have produced results comparable to and in some cases superior to human experts. However, the generated neural networks are typically regarded as incomprehensible black-box models, which not only limits their applications, but also hinders testing and verifying. In this paper, we present an active learning framework to extract automata from neural network classifiers, which can help users to understand the classifiers. In more detail, we use Angluin’s L* algorithm as a learner and the neural network under learning as an oracle, employing abstraction interpretation of the neural network for answering membership and equivalence queries. Our abstraction consists of value, symbol and word abstractions. The factors that may affect the abstraction are also discussed in the paper. We have implemented our approach in a prototype. To evaluate it, we have performed the prototype on a MNIST classifier and have identified that the abstraction with interval number 2 and block size 1 × 28 offers the best performance in terms of F1 score. We also have compared our extracted DFA against the DFAs learned via the passive learning algorithms provided in LearnLib and the experimental results show that our DFA gives a better performance on the MNIST dataset.

Damage detection in a novel deep-learning framework: a robust method for feature extraction

2019 ◽  
Vol 19 (2) ◽  
pp. 424-442 ◽  
Author(s):  
Tian Guo ◽  
Lianping Wu ◽  
Cunjun Wang ◽  
Zili Xu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Architecture ◽  
Mode Shapes ◽  
Damage Scenarios ◽  
Learning Modules ◽  
Learning Framework ◽  
Multi Scale ◽  
Extensive Evaluation ◽  
The Neural Network

Extracting damage features precisely while overcoming the adverse interferences of measurement noise and incomplete data is a problem demanding prompt solution in structural health monitoring (SHM). In this article, we present a deep-learning-based method that can extract the damage features from mode shapes without utilizing any hand-engineered feature or prior knowledge. To meet various requirements of the damage scenarios, we use convolutional neural network (CNN) algorithm and design a new network architecture: a multi-scale module, which helps in extracting features at various scales that can reduce the interference of contaminated data; stacked residual learning modules, which help in accelerating the network convergence; and a global average pooling layer, which helps in reducing the consumption of computing resources and obtaining a regression performance. An extensive evaluation of the proposed method is conducted by using datasets based on numerical simulations, along with two datasets based on laboratory measurements. The transferring parameter methodology is introduced to reduce retraining requirement without any decreases in precision. Furthermore, we plot the feature vectors of each layer to discuss the damage features learned at these layers and additionally provide the basis for explaining the working principle of the neural network. The results show that our proposed method has accuracy improvements of at least 10% over other network architectures.

Sign in / Sign up

Export Citation Format

Share Document