scholarly journals FABA: An Algorithm for Fast Aggregation against Byzantine Attacks in Distributed Neural Networks

2019 ◽  
Author(s):  
Qi Xia ◽  
Zeyi Tao ◽  
Zijiang Hao ◽  
Qun Li
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Single Machine ◽  
Large Scale ◽  
Efficient Solution ◽  
Distributed Training ◽  
Hardware Failures ◽  
Deep Learning Neural Network ◽  
Byzantine Attacks

Many times, training a large scale deep learning neural network on a single machine becomes more and more difficult for a complex network model. Distributed training provides an efficient solution, but Byzantine attacks may occur on participating workers. They may be compromised or suffer from hardware failures. If they upload poisonous gradients, the training will become unstable or even converge to a saddle point. In this paper, we propose FABA, a Fast Aggregation algorithm against Byzantine Attacks, which removes the outliers in the uploaded gradients and obtains gradients that are close to the true gradients. We show the convergence of our algorithm. The experiments demonstrate that our algorithm can achieve similar performance to non-Byzantine case and higher efficiency as compared to previous algorithms.

scholarly journals Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2852
Author(s):  
Parvathaneni Naga Srinivasu ◽  
Jalluri Gnana SivaSai ◽  
Muhammad Fazal Ijaz ◽  
Akash Kumar Bhoi ◽  
Wonjoon Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Skin Disease ◽  
Network Architecture ◽  
Large Scale ◽  
Short Term Memory ◽  
Convolutional Networks ◽  
Occurrence Matrix

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

scholarly journals Inverting Rayleigh surface wave velocities for crustal thickness in eastern Tibet and the western Yangtze craton based on deep learning neural networks

2019 ◽  
Vol 26 (2) ◽  
pp. 61-71 ◽  
Author(s):  
Xianqiong Cheng ◽  
Qihe Liu ◽  
Pingping Li ◽  
Yuan Liu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Surface Wave ◽  
Crustal Thickness ◽  
Rayleigh Surface Wave ◽  
Yangtze Craton ◽  
North West ◽  
Eastern Tibet ◽  
Deep Learning Neural Network

Abstract. Crustal thickness is an important factor affecting lithospheric structure and deep geodynamics. In this paper, a deep learning neural network based on a stacked sparse auto-encoder is proposed for the inversion of crustal thickness in eastern Tibet and the western Yangtze craton. First, with the phase velocity of the Rayleigh surface wave as input and the theoretical crustal thickness as output, 12 deep-sSAE neural networks are constructed, which are trained by 380 000 and tested by 120 000 theoretical models. We then invert the observed phase velocities through these 12 neural networks. According to the test error and misfit of other crustal thickness models, the optimal crustal thickness model is selected as the crustal thickness of the study area. Compared with other ways to detect crustal thickness such as seismic wave reflection and receiver function, we adopt a new way for inversion of earth model parameters, and realize that a deep learning neural network based on data driven with the highly non-linear mapping ability can be widely used by geophysicists, and our result has good agreement with high-resolution crustal thickness models. Compared with other methods, our experimental results based on a deep learning neural network and a new Rayleigh wave phase velocity model reveal some details: there is a northward-dipping Moho gradient zone in the Qiangtang block and a relatively shallow north-west–south-east oriented crust at the Songpan–Ganzi block. Crustal thickness around Xi'an and the Ordos basin is shallow, about 35 km. The change in crustal thickness in the Sichuan–Yunnan block is sharp, where crustal thickness is 60 km north-west and 35 km south-east. We conclude that the deep learning neural network is a promising, efficient, and believable geophysical inversion tool.

scholarly journals Enhancing PMW Satellite Precipitation Estimation: Detecting Convective Class

2019 ◽  
Vol 36 (12) ◽  
pp. 2349-2363 ◽  
Author(s):  
Veljko Petković ◽  
Marko Orescanin ◽  
Pierre Kirstetter ◽  
Christian Kummerow ◽  
Ralph Ferraro
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Large Scale ◽  
Model Development ◽  
Precipitation Rate ◽  
Neural Network Approach ◽  
Satellite Precipitation ◽  
Precipitation Estimation ◽  
Microwave Imager ◽  
Deep Learning Neural Network

AbstractA decades-long effort in observing precipitation from space has led to continuous improvements of satellite-derived passive microwave (PMW) large-scale precipitation products. However, due to a limited ability to relate observed radiometric signatures to precipitation type (convective and stratiform) and associated precipitation rate variability, PMW retrievals are prone to large systematic errors at instantaneous scales. The present study explores the use of deep learning approach in extracting the information content from PMW observation vectors to help identify precipitation types. A deep learning neural network model (DNN) is developed to retrieve the convective type in precipitating systems from PMW observations. A 12-month period of Global Precipitation Measurement mission Microwave Imager (GMI) observations is used as a dataset for model development and verification. The proposed DNN model is shown to accurately predict precipitation types for 85% of total precipitation volume. The model reduces precipitation rate bias associated with convective and stratiform precipitation in the GPM operational algorithm by a factor of 2 while preserving the correlation with reference precipitation rates, and is insensitive to surface type variability. Based on comparisons against currently used convective schemes, it is concluded that the neural network approach has the potential to address regime-specific PMW satellite precipitation biases affecting GPM operations.

scholarly journals Automatic Detection of Impervious Surfaces from Remotely Sensed Data Using Deep Learning

2021 ◽  
Vol 13 (16) ◽  
pp. 3166
Author(s):  
Jash R. Parekh ◽  
Ate Poortinga ◽  
Biplov Bhandari ◽  
Timothy Mayer ◽  
David Saah ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Large Scale ◽  
Mean Squared Error ◽  
Remotely Sensed ◽  
Landsat 8 ◽  
Impervious Surfaces ◽  
Remotely Sensed Data ◽  
Statistical Indices ◽  
Deep Learning Neural Network

The large scale quantification of impervious surfaces provides valuable information for urban planning and socioeconomic development. Remote sensing and GIS techniques provide spatial and temporal information of land surfaces and are widely used for modeling impervious surfaces. Traditionally, these surfaces are predicted by computing statistical indices derived from different bands available in remotely sensed data, such as the Landsat and Sentinel series. More recently, researchers have explored classification and regression techniques to model impervious surfaces. However, these modeling efforts are limited due to lack of labeled data for training and evaluation. This in turn requires significant effort for manual labeling of data and visual interpretation of results. In this paper, we train deep learning neural networks using TensorFlow to predict impervious surfaces from Landsat 8 images. We used OpenStreetMap (OSM), a crowd-sourced map of the world with manually interpreted impervious surfaces such as roads and buildings, to programmatically generate large amounts of training and evaluation data, thus overcoming the need for manual labeling. We conducted extensive experimentation to compare the performance of different deep learning neural network architectures, optimization methods, and the set of features used to train the networks. The four model configurations labeled U-Net_SGD_Bands, U-Net_Adam_Bands, U-Net_Adam_Bands+SI, and VGG-19_Adam_Bands+SI resulted in a root mean squared error (RMSE) of 0.1582, 0.1358, 0.1375, and 0.1582 and an accuracy of 90.87%, 92.28%, 92.46%, and 90.11%, respectively, on the test set. The U-Net_Adam_Bands+SI Model, similar to the others mentioned above, is a deep learning neural network that combines Landsat 8 bands with statistical indices. This model performs the best among all four on statistical accuracy and produces qualitatively sharper and brighter predictions of impervious surfaces as compared to the other models.

scholarly journals Generative Art: Between the Nodes of Neuron Networks

Artnodes ◽  
2020 ◽  
Author(s):  
Bruno Caldas Vianna
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Generative Art ◽  
Creation Process ◽  
Neuron Networks ◽  
Starting Point ◽  
Deep Learning Neural Network ◽  
In The Beginning

This article uses the exhibition “Infinite Skulls”, which happened in Paris in the beginning of 2019, as a starting point to discuss art created by artificial intelligence and, by extension, unique pieces of art generated by algorithms. We detail the development of DCGAN, the deep learning neural network used in the show, from its cybernetics origin. The show and its creation process are described, identifying elements of creativity and technique, as well as question of the authorship of works. Then it frames these works in the context of generative art, pointing affinities and differences, and the issues of representing through procedures and abstractions. It describes the major breakthrough of neural network for technical images as the ability to represent categories through an abstraction, rather than images themselves. Finally, it tries to understand neural networks more as a tool for artists than an autonomous art creator.

Deep learning neural network for the prediction of asian tiger stock markets

2021 ◽  
pp. 2150040
Author(s):  
Kok-Leong Yap ◽  
Wee-Yeap Lau ◽  
Izlin Ismail
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Stock Prices ◽  
Stock Markets ◽  
Short Term Memory ◽  
Stock Market Index ◽  
Short Term ◽  
Asian Tiger ◽  
Deep Learning Neural Network

Motivated by the recent interest of stock traders and investors towards the deep learning neural network, this study employs the deep learning neural networks, namely, multilayer perceptron, long short-term memory, and convolutional neural network, to forecast the Asian Tiger stock markets. One of the challenges to using deep learning neural networks is to select the input variable. We propose to use multiple linear regression to select the input variable that is significant to the output. Besides, we construct a regional stock market index as a significant input to forecast the Asian Tiger stock markets. A comparison study on the forecasting model shows that the deep learning model can be used as a decision-making system that assists investors to predict short-term movement and trends of stock prices.

scholarly journals SURVEY ON EVOLVING DEEP LEARNING NEURAL NETWORK ARCHITECTURES

2019 ◽  
Vol 2019 (2) ◽  
pp. 73-82 ◽  
Author(s):  
Dr. Abul Bashar
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Feature Extraction ◽  
Deep Learning ◽  
Human Performance ◽  
Deep Neural Networks ◽  
Network Architectures ◽  
Neural Network Architectures ◽  
Deep Learning Neural Network

The deep learning being a subcategory of the machine learning follows the human instincts of learning by example to produce accurate results. The deep learning performs training to the computer frame work to directly classify the tasks from the documents available either in the form of the text, image, or the sound. Most often the deep learning utilizes the neural network to perform the accurate classification and is referred as the deep neural networks; one of the most common deep neural networks used in a broader range of applications is the convolution neural network that provides an automated way of feature extraction by learning the features directly from the images or the text unlike the machine learning that extracts the features manually. This enables the deep learning neural networks to have a state of art accuracy that mostly expels even the human performance. So the paper is to present the survey on the deep learning neural network architectures utilized in various applications for having an accurate classification with an automated feature extraction.

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

Sign in / Sign up

Export Citation Format

Share Document