scholarly journals SNR: S queezing N umerical R ange Defuses Bit Error Vulnerability Surface in Deep Neural Networks

2021 ◽  
Vol 20 (5s) ◽  
pp. 1-25
Author(s):  
Elbruz Ozen ◽  
Alex Orailoglu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Low Cost ◽  
Error Resilience ◽  
Error Rates ◽  
Training Methods ◽  
Performance Requirements ◽  
Proper Design ◽  
And Performance

As deep learning algorithms are widely adopted, an increasing number of them are positioned in embedded application domains with strict reliability constraints. The expenditure of significant resources to satisfy performance requirements in deep neural network accelerators has thinned out the margins for delivering safety in embedded deep learning applications, thus precluding the adoption of conventional fault tolerance methods. The potential of exploiting the inherent resilience characteristics of deep neural networks remains though unexplored, offering a promising low-cost path towards safety in embedded deep learning applications. This work demonstrates the possibility of such exploitation by juxtaposing the reduction of the vulnerability surface through the proper design of the quantization schemes with shaping the parameter distributions at each layer through the guidance offered by appropriate training methods, thus delivering deep neural networks of high resilience merely through algorithmic modifications. Unequaled error resilience characteristics can be thus injected into safety-critical deep learning applications to tolerate bit error rates of up to at absolutely zero hardware, energy, and performance costs while improving the error-free model accuracy even further.

scholarly journals Examining Attention Mechanisms in Deep Learning Models for Sentiment Analysis

2021 ◽  
Vol 11 (9) ◽  
pp. 3883
Author(s):  
Spyridon Kardakis ◽  
Isidoros Perikos ◽  
Foteini Grivokostopoulou ◽  
Ioannis Hatzilygeroudis
Keyword(s):  
Neural Networks ◽  
Experimental Study ◽  
Deep Learning ◽  
Comparative Analysis ◽  
Sentiment Analysis ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Training Methods ◽  
Learning Models ◽  
Neural Models

Attention-based methods for deep neural networks constitute a technique that has attracted increased interest in recent years. Attention mechanisms can focus on important parts of a sequence and, as a result, enhance the performance of neural networks in a variety of tasks, including sentiment analysis, emotion recognition, machine translation and speech recognition. In this work, we study attention-based models built on recurrent neural networks (RNNs) and examine their performance in various contexts of sentiment analysis. Self-attention, global-attention and hierarchical-attention methods are examined under various deep neural models, training methods and hyperparameters. Even though attention mechanisms are a powerful recent concept in the field of deep learning, their exact effectiveness in sentiment analysis is yet to be thoroughly assessed. A comparative analysis is performed in a text sentiment classification task where baseline models are compared with and without the use of attention for every experiment. The experimental study additionally examines the proposed models’ ability in recognizing opinions and emotions in movie reviews. The results indicate that attention-based models lead to great improvements in the performance of deep neural models showcasing up to a 3.5% improvement in their accuracy.

scholarly journals Estimating the Composition of Food Nutrients from Hyperspectral Signals Based on Deep Neural Networks

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1560 ◽  
Author(s):  
DaeHan Ahn ◽  
Ji-Young Choi ◽  
Hee-Chul Kim ◽  
Jeong-Seok Cho ◽  
Kwang-Deog Moon ◽  
...  
Keyword(s):  
Neural Networks ◽  
Performance Evaluation ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Low Cost ◽  
Estimation Accuracy ◽  
Weight Changes ◽  
New Approach ◽  
Comprehensive Performance ◽  
Increasing Demand

There is an increasing demand for acquiring details of food nutrients especially among those who are sensitive to food intakes and weight changes. To meet this need, we propose a new approach based on deep learning that precisely estimates the composition of carbohydrates, proteins, and fats from hyperspectral signals of foods obtained by using low-cost spectrometers. Specifically, we develop a system consisting of multiple deep neural networks for estimating food nutrients followed by detecting and discarding estimation anomalies. Our comprehensive performance evaluation demonstrates that the proposed system can maximize estimation accuracy by automatically identifying wrong estimations. As such, if consolidated with the capability of reinforcement learning, it will likely be positioned as a promising means for personalized healthcare in terms of food safety.

scholarly journals Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1579
Author(s):  
Dongqi Wang ◽  
Qinghua Meng ◽  
Dongming Chen ◽  
Hupo Zhang ◽  
Lisheng Xu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Channel Model ◽  
Expert Knowledge ◽  
Automatic Detection ◽  
Data Representation ◽  
Learning Technology ◽  
Arrhythmia Detection ◽  
Automatic Feature Extraction

Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on deep neural networks has been widely discussed. In order to utilize the complementary strength between different schemes, in this paper, we propose an arrhythmia detection method based on the multi-resolution representation (MRR) of ECG signals. This method utilizes four different up to date deep neural networks as four channel models for ECG vector representations learning. The deep learning based representations, together with hand-crafted features of ECG, forms the MRR, which is the input of the downstream classification strategy. The experimental results of big ECG dataset multi-label classification confirm that the F1 score of the proposed method is 0.9238, which is 1.31%, 0.62%, 1.18% and 0.6% higher than that of each channel model. From the perspective of architecture, this proposed method is highly scalable and can be employed as an example for arrhythmia recognition.

scholarly journals Assurance monitoring of learning-enabled cyber-physical systems using inductive conformal prediction based on distance learning

2021 ◽  
Vol 35 (2) ◽  
pp. 251-264
Author(s):  
Dimitrios Boursinos ◽  
Xenofon Koutsoukos
Keyword(s):  
Neural Networks ◽  
Distance Learning ◽  
Real Time ◽  
Speaker Recognition ◽  
Deep Neural Networks ◽  
Cyber Physical Systems ◽  
Error Rates ◽  
Traffic Sign ◽  
Conformal Prediction ◽  
Physical Systems

AbstractMachine learning components such as deep neural networks are used extensively in cyber-physical systems (CPS). However, such components may introduce new types of hazards that can have disastrous consequences and need to be addressed for engineering trustworthy systems. Although deep neural networks offer advanced capabilities, they must be complemented by engineering methods and practices that allow effective integration in CPS. In this paper, we proposed an approach for assurance monitoring of learning-enabled CPS based on the conformal prediction framework. In order to allow real-time assurance monitoring, the approach employs distance learning to transform high-dimensional inputs into lower size embedding representations. By leveraging conformal prediction, the approach provides well-calibrated confidence and ensures a bounded small error rate while limiting the number of inputs for which an accurate prediction cannot be made. We demonstrate the approach using three datasets of mobile robot following a wall, speaker recognition, and traffic sign recognition. The experimental results demonstrate that the error rates are well-calibrated while the number of alarms is very small. Furthermore, the method is computationally efficient and allows real-time assurance monitoring of CPS.

scholarly journals Mobility-Included DNN Partition Offloading from Mobile Devices to Edge Clouds

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 229
Author(s):  
Xianzhong Tian ◽  
Juan Zhu ◽  
Ting Xu ◽  
Yanjun Li
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Mobile Devices ◽  
Wireless Network ◽  
Deep Neural Networks ◽  
Mobile User ◽  
Computation Offloading ◽  
Long Latency ◽  
Total Latency ◽  
And Performance

The latest results in Deep Neural Networks (DNNs) have greatly improved the accuracy and performance of a variety of intelligent applications. However, running such computation-intensive DNN-based applications on resource-constrained mobile devices definitely leads to long latency and huge energy consumption. The traditional way is performing DNNs in the central cloud, but it requires significant amounts of data to be transferred to the cloud over the wireless network and also results in long latency. To solve this problem, offloading partial DNN computation to edge clouds has been proposed, to realize the collaborative execution between mobile devices and edge clouds. In addition, the mobility of mobile devices is easily to cause the computation offloading failure. In this paper, we develop a mobility-included DNN partition offloading algorithm (MDPO) to adapt to user’s mobility. The objective of MDPO is minimizing the total latency of completing a DNN job when the mobile user is moving. The MDPO algorithm is suitable for both DNNs with chain topology and graphic topology. We evaluate the performance of our proposed MDPO compared to local-only execution and edge-only execution, experiments show that MDPO significantly reduces the total latency and improves the performance of DNN, and MDPO can adjust well to different network conditions.

scholarly journals Computational Complexity Reduction of Neural Networks of Brain Tumor Image Segmentation by Introducing Fermi–Dirac Correction Functions

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 223
Author(s):  
Yen-Ling Tai ◽  
Shin-Jhe Huang ◽  
Chien-Chang Chen ◽  
Henry Horng-Shing Lu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Computational Complexity ◽  
High Performance ◽  
Low Cost ◽  
Structural Complexity ◽  
Correction Function ◽  
Computational Time ◽  
Learning Methods ◽  
Band Theory

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

scholarly journals Experiments with Neural Networks in the Identification and Control of a Magnetic Levitation System Using a Low-Cost Platform

2021 ◽  
Vol 11 (6) ◽  
pp. 2535
Author(s):  
Bruno E. Silva ◽  
Ramiro S. Barbosa
Keyword(s):  
Neural Networks ◽  
Neural Control ◽  
Magnetic Levitation ◽  
Low Cost ◽  
Training Data ◽  
Neural Controllers ◽  
Levitation System ◽  
Internal Model Controller ◽  
Magnetic Levitation System ◽  
And Performance

In this article, we designed and implemented neural controllers to control a nonlinear and unstable magnetic levitation system composed of an electromagnet and a magnetic disk. The objective was to evaluate the implementation and performance of neural control algorithms in a low-cost hardware. In a first phase, we designed two classical controllers with the objective to provide the training data for the neural controllers. After, we identified several neural models of the levitation system using Nonlinear AutoRegressive eXogenous (NARX)-type neural networks that were used to emulate the forward dynamics of the system. Finally, we designed and implemented three neural control structures: the inverse controller, the internal model controller, and the model reference controller for the control of the levitation system. The neural controllers were tested on a low-cost Arduino control platform through MATLAB/Simulink. The experimental results proved the good performance of the neural controllers.

scholarly journals Enabling deeper learning on big data for materials informatics applications

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dipendra Jha ◽  
Vishu Gupta ◽  
Logan Ward ◽  
Zijiang Yang ◽  
Christopher Wolverton ◽  
...  
Keyword(s):  
Neural Networks ◽  
Big Data ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Materials Science ◽  
Prediction Models ◽  
Model Performance ◽  
Materials Informatics ◽  
Learning Framework ◽  
Significant Attention

AbstractThe application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

Sign in / Sign up

Export Citation Format

Share Document