scholarly journals Quantization of Deep Neural Networks for Accurate Edge Computing

2021 ◽  
Vol 17 (4) ◽  
pp. 1-11
Author(s):  
Wentao Chen ◽  
Hailong Qiu ◽  
Jian Zhuang ◽  
Chutong Zhang ◽  
Yu Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Segmentation ◽  
Automatic Speech Recognition ◽  
Deep Neural Networks ◽  
Biomedical Image ◽  
Wide Range ◽  
Improve Accuracy ◽  
Memory Reduction ◽  
Fully Connected

Deep neural networks have demonstrated their great potential in recent years, exceeding the performance of human experts in a wide range of applications. Due to their large sizes, however, compression techniques such as weight quantization and pruning are usually applied before they can be accommodated on the edge. It is generally believed that quantization leads to performance degradation, and plenty of existing works have explored quantization strategies aiming at minimum accuracy loss. In this paper, we argue that quantization, which essentially imposes regularization on weight representations, can sometimes help to improve accuracy. We conduct comprehensive experiments on three widely used applications: fully connected network for biomedical image segmentation, convolutional neural network for image classification on ImageNet, and recurrent neural network for automatic speech recognition, and experimental results show that quantization can improve the accuracy by 1%, 1.95%, 4.23% on the three applications respectively with 3.5x-6.4x memory reduction.

scholarly journals A HYBRID MODEL USING THE PRETRAINED BERT AND DEEP NEURAL NETWORKS WITH RICH FEATURE FOR EXTRACTIVE TEXT SUMMARIZATION

2021 ◽  
Vol 37 (2) ◽  
pp. 123-143
Author(s):  
Tuan Minh Luu ◽  
Huong Thanh Le ◽  
Tan Minh Hoang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Text Summarization ◽  
Training Dataset ◽  
Extractive Summarization ◽  
Input Text ◽  
Summarization System ◽  
Fully Connected

Deep neural networks have been applied successfully to extractive text summarization tasks with the accompany of large training datasets. However, when the training dataset is not large enough, these models reveal certain limitations that affect the quality of the system’s summary. In this paper, we propose an extractive summarization system basing on a Convolutional Neural Network and a Fully Connected network for sentence selection. The pretrained BERT multilingual model is used to generate embeddings vectors from the input text. These vectors are combined with TF-IDF values to produce the input of the text summarization system. Redundant sentences from the output summary are eliminated by the Maximal Marginal Relevance method. Our system is evaluated with both English and Vietnamese languages using CNN and Baomoi datasets, respectively. Experimental results show that our system achieves better results comparing to existing works using the same dataset. It confirms that our approach can be effectively applied to summarize both English and Vietnamese languages.

scholarly journals Distinguishing between recent balancing selection and incomplete sweep using deep neural networks

2020 ◽  
Author(s):  
Ulas Isildak ◽  
Alessandro Stella ◽  
Matteo Fumagalli
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Balancing Selection ◽  
False Positive Rate ◽  
Genomic Data ◽  
Training Data ◽  
Functional Changes ◽  
Wide Range ◽  
Recent Selection

1AbstractBalancing selection is an important adaptive mechanism underpinning a wide range of phenotypes. Despite its relevance, the detection of recent balancing selection from genomic data is challenging as its signatures are qualitatively similar to those left by ongoing positive selection. In this study we developed and implemented two deep neural networks and tested their performance to predict loci under recent selection, either due to balancing selection or incomplete sweep, from population genomic data. Specifically, we generated forward-intime simulations to train and test an artificial neural network (ANN) and a convolutional neural network (CNN). ANN received as input multiple summary statistics calculated on the locus of interest, while CNN was applied directly on the matrix of haplotypes. We found that both architectures have high accuracy to identify loci under recent selection. CNN generally outperformed ANN to distinguish between signals of balancing selection and incomplete sweep and was less affected by incorrect training data. We deployed both trained networks on neutral genomic regions in European populations and demonstrated a lower false positive rate for CNN than ANN. We finally deployed CNN within the MEFV gene region and identified several common variants predicted to be under incomplete sweep in a European population. Notably, two of these variants are functional changes and could modulate susceptibility to Familial Mediterranean Fever, possibly as a consequence of past adaptation to pathogens. In conclusion, deep neural networks were able to characterise signals of selection on intermediate-frequency variants, an analysis currently inaccessible by commonly used strategies.

Parameter Setting for Deep Neural Networks Using Swarm Intelligence on Phishing Websites Classification

2019 ◽  
Vol 28 (06) ◽  
pp. 1960008 ◽  
Author(s):  
Grega Vrbančič ◽  
Iztok Fister ◽  
Vili Podgorelec
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Swarm Intelligence ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Predictive Performance ◽  
Parameter Setting ◽  
The Past ◽  
Wide Range ◽  
Learning Architectures

Over the past years, the application of deep neural networks in a wide range of areas is noticeably increasing. While many state-of-the-art deep neural networks are providing the performance comparable or in some cases even superior to humans, major challenges such as parameter settings for learning deep neural networks and construction of deep learning architectures still exist. The implications of those challenges have a significant impact on how a deep neural network is going to perform on a specific task. With the proposed method, presented in this paper, we are addressing the problem of parameter setting for a deep neural network utilizing swarm intelligence algorithms. In our experiments, we applied the proposed method variants to the classification task for distinguishing between phishing and legitimate websites. The performance of the proposed method is evaluated and compared against four different phishing datasets, two of which we prepared on our own. The results, obtained from the conducted empirical experiments, have proven the proposed approach to be very promising. By utilizing the proposed swarm intelligence based methods, we were able to statistically significantly improve the predictive performance when compared to the manually tuned deep neural network. In general, the improvement of classification accuracy ranges from 2.5% to 3.8%, while the improvement of F1-score reached even 24% on one of the datasets.

scholarly journals Memristor crossbar architectures for implementing deep neural networks

2021 ◽  
Author(s):  
Xiaoyang Liu ◽  
Zhigang Zeng
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Neural Networks ◽  
Activation Functions ◽  
Simulation Results ◽  
Memristor Crossbars ◽  
Memristor Crossbar ◽  
Fully Connected

AbstractThe paper presents memristor crossbar architectures for implementing layers in deep neural networks, including the fully connected layer, the convolutional layer, and the pooling layer. The crossbars achieve positive and negative weight values and approximately realize various nonlinear activation functions. Then the layers constructed by the crossbars are adopted to build the memristor-based multi-layer neural network (MMNN) and the memristor-based convolutional neural network (MCNN). Two kinds of in-situ weight update schemes, which are the fixed-voltage update and the approximately linear update, respectively, are used to train the networks. Consider variations resulted from the inherent characteristics of memristors and the errors of programming voltages, the robustness of MMNN and MCNN to these variations is analyzed. The simulation results on standard datasets show that deep neural networks (DNNs) built by the memristor crossbars work satisfactorily in pattern recognition tasks and have certain robustness to memristor variations.

Deep distributed convolutional neural networks: Universality

2018 ◽  
Vol 16 (06) ◽  
pp. 895-919 ◽  
Author(s):  
Ding-Xuan Zhou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Mathematical Foundation ◽  
Deep Convolutional Neural Networks ◽  
The Family ◽  
Fully Connected

Deep learning based on structured deep neural networks has provided powerful applications in various fields. The structures imposed on the deep neural networks are crucial, which makes deep learning essentially different from classical schemes based on fully connected neural networks. One of the commonly used deep neural network structures is generated by convolutions. The produced deep learning algorithms form the family of deep convolutional neural networks. Despite of their power in some practical domains, little is known about the mathematical foundation of deep convolutional neural networks such as universality of approximation. In this paper, we propose a family of new structured deep neural networks: deep distributed convolutional neural networks. We show that these deep neural networks have the same order of computational complexity as the deep convolutional neural networks, and we prove their universality of approximation. Some ideas of our analysis are from ridge approximation, wavelets, and learning theory.

scholarly journals Using Summary Layers to Probe Neural Network Behaviour

2020 ◽  
Vol 32 (2) ◽  
Author(s):  
Marelie Hattingh Davel
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Network Architectures ◽  
Feedforward Networks ◽  
Empirical Results ◽  
Analysis Process ◽  
Generalisation Ability ◽  
Neural Network Architectures ◽  
Fully Connected

No framework exists that can explain and predict the generalisation ability of deep neural networks in general circumstances. In fact, this question has not been answered for some of the least complicated of neural network architectures: fully-connected feedforward networks with rectified linear activations and a limited number of hidden layers. For such an architecture, we show how adding a summary layer to the network makes it more amenable to analysis, and allows us to define the conditions that are required to guarantee that a set of samples will all be classified correctly. This process does not describe the generalisation behaviour of these networks, but produces a number of metrics that are useful for probing their learning and generalisation behaviour. We support the analytical conclusions with empirical results, both to confirm that the mathematical guarantees hold in practice, and to demonstrate the use of the analysis process.

scholarly journals Deep Neural Networks Point to Mid-level Complexity of Rodent Object Vision

2020 ◽  
Author(s):  
Kasper Vinken ◽  
Hans Op de Beeck
Keyword(s):  
Neural Networks ◽  
Information Processing ◽  
Object Recognition ◽  
Deep Neural Networks ◽  
Convincing Evidence ◽  
Complex Object ◽  
Visual Neuroscience ◽  
Wide Range ◽  
Invariant Object Recognition ◽  
Fully Connected

AbstractIn the last two decades rodents have been on the rise as a dominant model for visual neuroscience. This is particularly true for earlier levels of information processing, but high-profile papers have suggested that also higher levels of processing such as invariant object recognition occur in rodents. Here we provide a quantitative and comprehensive assessment of this claim by comparing a wide range of rodent behavioral and neural data with convolutional deep neural networks. These networks have been shown to capture the richness of information processing in primates through a succession of convolutional and fully connected layers. We find that rodent object vision can be captured using low to mid-level convolutional layers only, without any convincing evidence for the need of higher layers known to simulate complex object recognition in primates. Our approach also reveals surprising insights on assumptions made before, for example, that the best performing animals would be the ones using the most complex representations – which we show to likely be incorrect. Our findings suggest a road ahead for further studies aiming at quantifying and establishing the richness of representations underlying information processing in animal models at large.

scholarly journals Physics Inspired Deep Neural Networks for Top Quark Reconstruction

2020 ◽  
Vol 245 ◽  
pp. 06029
Author(s):  
Kevin Greif ◽  
Kevin Lannon
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Top Quark ◽  
Deep Neural Networks ◽  
Great Success ◽  
Fully Connected

Deep neural networks (DNNs) have been applied to the fields of computer vision and natural language processing with great success in recent years. The success of these applications has hinged on the development of specialized DNN architectures that take advantage of specific characteristics of the problem to be solved, namely convolutional neural networks for computer vision and recurrent neural networks for natural language processing. This research explores whether a neural network architecture specific to the task of identifying t → Wb decays in particle collision data yields better performance than a generic, fully-connected DNN. Although applied here to resolved top quark decays, this approach is inspired by an DNN technique for tagging boosted top quarks, which consists of defining custom neural network layers known as the combination and Lorentz layers. These layers encode knowledge of relativistic kinematics applied to combinations of particles, and the output of these specialized layers can then be fed into a fully connected neural network to learn tasks such as classification. This research compares the performance of these physics inspired networks to that of a generic, fully-connected DNN, to see if there is any advantage in terms of classification performance, size of the network, or ease of training.

scholarly journals Deep Neural Networks and Kernel Regression Achieve Comparable Accuracies for Functional Connectivity Prediction of Behavior and Demographics

2018 ◽  
Author(s):  
Tong He ◽  
Ru Kong ◽  
Avram J. Holmes ◽  
Minh Nguyen ◽  
Mert R. Sabuncu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Functional Connectivity ◽  
Sample Size ◽  
Deep Neural Networks ◽  
Kernel Regression ◽  
Feedforward Neural Network ◽  
Uk Biobank ◽  
Similar Performance ◽  
Wide Range

AbstractThere is significant interest in the development and application of deep neural networks (DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their classical counterparts in a variety of neuroimaging applications, yet there are few direct comparisons of relative utility. Here, we compared the performance of three DNN architectures and a classical machine learning algorithm (kernel regression) in predicting individual phenotypes from whole-brain resting-state functional connectivity (RSFC) patterns. One of the DNNs was a generic fully-connected feedforward neural network, while the other two DNNs were recently published approaches specifically designed to exploit the structure of connectome data. By using a combined sample of almost 10,000 participants from the Human Connectome Project (HCP) and UK Biobank, we showed that the three DNNs and kernel regression achieved similar performance across a wide range of behavioral and demographic measures. Furthermore, the generic feedforward neural network exhibited similar performance to the two state-of-the-art connectome-specific DNNs. When predicting fluid intelligence in the UK Biobank, performance of all algorithms dramatically improved when sample size increased from 100 to 1000 subjects. Improvement was smaller, but still significant, when sample size increased from 1000 to 5000 subjects. Importantly, kernel regression was competitive across all sample sizes. Overall, our study suggests that kernel regression is as effective as DNNs for RSFC-based behavioral prediction, while incurring significantly lower computational costs. Therefore, kernel regression might serve as a useful baseline algorithm for future studies.

Sign in / Sign up

Export Citation Format

Share Document