scholarly journals Fastened CROWN: Tightened Neural Network Robustness Certificates

2020 ◽  
Vol 34 (04) ◽  
pp. 5037-5044
Author(s):  
Zhaoyang Lyu ◽  
Ching-Yun Ko ◽  
Zhifeng Kong ◽  
Ngai Wong ◽  
Dahua Lin ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Programming ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Convex Relaxation ◽  
Real Life ◽  
Network Robustness ◽  
The Past ◽  
Computationally Expensive

The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reliable evaluations of the fragility level in different deep neural networks. Apart from devising adversarial attacks, quantifiers that certify safeguarded regions have also been designed in the past five years. The summarizing work in (Salman et al. 2019) unifies a family of existing verifiers under a convex relaxation framework. We draw inspiration from such work and further demonstrate the optimality of deterministic CROWN (Zhang et al. 2018) solutions in a given linear programming problem under mild constraints. Given this theoretical result, the computationally expensive linear programming based method is shown to be unnecessary. We then propose an optimization-based approach FROWN (Fastened CROWN): a general algorithm to tighten robustness certificates for neural networks. Extensive experiments on various networks trained individually verify the effectiveness of FROWN in safeguarding larger robust regions.

scholarly journals Semiotic Aggregation in Deep Learning

Entropy ◽  
2020 ◽  
Vol 22 (12) ◽  
pp. 1365
Author(s):  
Bogdan Muşat ◽  
Răzvan Andonie
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Decision Model ◽  
Deep Neural Networks ◽  
Neural Model ◽  
Network Layers ◽  
Saliency Maps ◽  
Spatial Entropy ◽  
Insight Into

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In our experiments, we visualize the superization process and show how the obtained knowledge can be used to explain the neural decision model. In addition, we attempt to optimize the architecture of the neural model employing a semiotic greedy technique. To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.

scholarly journals A Comparison of Optimization Algorithms for Deep Learning

2020 ◽  
Vol 34 (13) ◽  
pp. 2052013 ◽  
Author(s):  
Derya Soydaner
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Optimization Algorithms ◽  
Gradient Methods ◽  
The Past ◽  
Basic Optimization ◽  
In The Wild ◽  
Image Datasets

In recent years, we have witnessed the rise of deep learning. Deep neural networks have proved their success in many areas. However, the optimization of these networks has become more difficult as neural networks going deeper and datasets becoming bigger. Therefore, more advanced optimization algorithms have been proposed over the past years. In this study, widely used optimization algorithms for deep learning are examined in detail. To this end, these algorithms called adaptive gradient methods are implemented for both supervised and unsupervised tasks. The behavior of the algorithms during training and results on four image datasets, namely, MNIST, CIFAR-10, Kaggle Flowers and Labeled Faces in the Wild are compared by pointing out their differences against basic optimization algorithms.

Identification of Thoracic Diseases by Exploiting Deep Neural Networks (Preprint)

2020 ◽  
Author(s):  
Albahli Saleh ◽  
Ali Alkhalifah
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Medical Image Analysis ◽  
Medical Community ◽  
Learning Models ◽  
X Ray ◽  
Chest Disease

BACKGROUND To diagnose cardiothoracic diseases, a chest x-ray (CXR) is examined by a radiologist. As more people get affected, doctors are becoming scarce especially in developing countries. However, with the advent of image processing tools, the task of diagnosing these cardiothoracic diseases has seen great progress. A lot of researchers have put in work to see how the problems associated with medical images can be mitigated by using neural networks. OBJECTIVE Previous works used state-of-the-art techniques and got effective results with one or two cardiothoracic diseases but could lead to misclassification. In our work, we adopted GANs to synthesize the chest radiograph (CXR) to augment the training set on multiple cardiothoracic diseases to efficiently diagnose the chest diseases in different classes as shown in Figure 1. In this regard, our major contributions are classifying various cardiothoracic diseases to detect a specific chest disease based on CXR, use the advantage of GANs to overcome the shortages of small training datasets, address the problem of imbalanced data; and implementing optimal deep neural network architecture with different hyper-parameters to improve the model with the best accuracy. METHODS For this research, we are not building a model from scratch due to computational restraints as they require very high-end computers. Rather, we use a Convolutional Neural Network (CNN) as a class of deep neural networks to propose a generative adversarial network (GAN) -based model to generate synthetic data for training the data as the amount of the data is limited. We will use pre-trained models which are models that were trained on a large benchmark dataset to solve a problem similar to the one we want to solve. For example, the ResNet-152 model we used was initially trained on the ImageNet dataset. RESULTS After successful training and validation of the models we developed, ResNet-152 with image augmentation proved to be the best model for the automatic detection of cardiothoracic disease. However, one of the main problems associated with radiographic deep learning projects and research is the scarcity and unavailability of enough datasets which is a key component of all deep learning models as they require a lot of data for training. This is the reason why some of our models had image augmentation to increase the number of images without duplication. As more data are collected in the field of chest radiology, the models could be retrained to improve the accuracies of the models as deep learning models improve with more data. CONCLUSIONS This research employs the advantages of computer vision and medical image analysis to develop an automated model that has the clinical potential for early detection of the disease. Using deep learning models, the research aims to evaluate the effectiveness and accuracy of different convolutional neural network models in the automatic diagnosis of cardiothoracic diseases from x-ray images compared to diagnosis by experts in the medical community.

scholarly journals Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection

mSphere ◽  
2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Artur Yakimovich ◽  
Moona Huttunen ◽  
Jerzy Samolej ◽  
Barbara Clough ◽  
Nagisa Yoshida ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Network Evolution ◽  
Great Promise ◽  
Data Sets ◽  
Imaging Data ◽  
Data Set ◽  
Novel Strategy

ABSTRACT The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified data sets for rapid network evolution. Here, we present a novel strategy, termed “mimicry embedding,” for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets. IMPORTANCE In biology, the use of deep neural networks (DNNs) for analysis of pathogen infection is hampered by a lack of large verified data sets needed for rapid network evolution. Artificial neural networks detect handwritten digits with high precision thanks to large data sets, such as MNIST, that allow nearly unlimited training. Here, we developed a novel strategy we call mimicry embedding, which allows artificial intelligence (AI)-based analysis of variable pathogen-host data sets. We show that deep learning can be used to detect and classify single pathogens based on small differences.

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 An optical neural network using less than 1 photon per multiplication

2022 ◽  
Vol 13 (1) ◽  
Author(s):  
Tianyu Wang ◽  
Shi-Yuan Ma ◽  
Logan G. Wright ◽  
Tatsuhiro Onodera ◽  
Brian C. Richard ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Fundamental Principle ◽  
Energy Costs ◽  
Network Architectures ◽  
Optical Neural Networks ◽  
Optical Neural Network ◽  
Handwritten Digit

AbstractDeep learning has become a widespread tool in both science and industry. However, continued progress is hampered by the rapid growth in energy costs of ever-larger deep neural networks. Optical neural networks provide a potential means to solve the energy-cost problem faced by deep learning. Here, we experimentally demonstrate an optical neural network based on optical dot products that achieves 99% accuracy on handwritten-digit classification using ~3.1 detected photons per weight multiplication and ~90% accuracy using ~0.66 photons (~2.5 × 10−19 J of optical energy) per weight multiplication. The fundamental principle enabling our sub-photon-per-multiplication demonstration—noise reduction from the accumulation of scalar multiplications in dot-product sums—is applicable to many different optical-neural-network architectures. Our work shows that optical neural networks can achieve accurate results using extremely low optical energies.

scholarly journals Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training

2021 ◽  
Vol 118 (43) ◽  
pp. e2103091118
Author(s):  
Cong Fang ◽  
Hangfeng He ◽  
Qi Long ◽  
Weijie J. Su
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Model Minority ◽  
Tight Frame ◽  
Learning Models ◽  
The Neural Network ◽  
Long Time ◽  
Topmost Layer

In this paper, we introduce the Layer-Peeled Model, a nonconvex, yet analytically tractable, optimization program, in a quest to better understand deep neural networks that are trained for a sufficiently long time. As the name suggests, this model is derived by isolating the topmost layer from the remainder of the neural network, followed by imposing certain constraints separately on the two parts of the network. We demonstrate that the Layer-Peeled Model, albeit simple, inherits many characteristics of well-trained neural networks, thereby offering an effective tool for explaining and predicting common empirical patterns of deep-learning training. First, when working on class-balanced datasets, we prove that any solution to this model forms a simplex equiangular tight frame, which, in part, explains the recently discovered phenomenon of neural collapse [V. Papyan, X. Y. Han, D. L. Donoho, Proc. Natl. Acad. Sci. U.S.A. 117, 24652–24663 (2020)]. More importantly, when moving to the imbalanced case, our analysis of the Layer-Peeled Model reveals a hitherto-unknown phenomenon that we term Minority Collapse, which fundamentally limits the performance of deep-learning models on the minority classes. In addition, we use the Layer-Peeled Model to gain insights into how to mitigate Minority Collapse. Interestingly, this phenomenon is first predicted by the Layer-Peeled Model before being confirmed by our computational experiments.

scholarly journals Autonomous Tomato Harvesting Robotic System in Greenhouses: Deep Learning Classification

Mekatronika ◽  
2019 ◽  
Vol 1 (1) ◽  
pp. 80-86
Author(s):  
Ooi Peng Toon ◽  
Muhammad Aizzat Zakaria ◽  
Ahmad Fakhri Ab. Nasir ◽  
Anwar P.P. Abdul Majeed ◽  
Chung Young Tan ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
South America ◽  
Solanum Lycopersicum ◽  
Training Data ◽  
New Classification ◽  
The Past ◽  
Testing Data ◽  
Harvesting Robot

Solanum lycopersicum or generally known as tomato came from countries of South America and has been growing in many tropical countries and its healthy nutrients in tomato becomes one of the food demand by the locals in Malaysia when their lifestyle shifted to more concern for healthy food. Since export value and production has increased for the past few years, a vast amount of labours considered for the fruit-picking process. Hence, farmers are now preferring to look for automation to replace labour problems and high cost that they are facing. To pick a correct fruit within clusters, a harvesting robot requires guidance so that it can detect a fruit accurately. In this study, a new classification algorithm using deep learning specifically convolution neural network to classify the image is either a tomato or not tomato and next, the image is classified into either a ripe or unripe tomato. Furthermore, there are two classification neural networks which are tomato or not tomato and ripe and unripe tomato. Each network consists of 600 training data and 33 testing data. The accuracies that obtained from network 1 (tomato or not tomato) and network 2 (ripe or unripe tomato) are 76.366% and 98.788% respectively.

scholarly journals Tri-net for Semi-Supervised Deep Learning

2018 ◽  
Author(s):  
Dong-Dong Chen ◽  
Wei Wang ◽  
Wei Gao ◽  
Zhi-Hua Zhou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Error Rate ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Fine Tuning ◽  
Learning Methods ◽  
Model Initialization

Deep neural networks have witnessed great successes in various real applications, but it requires a large number of labeled data for training. In this paper, we propose tri-net, a deep neural network which is able to use massive unlabeled data to help learning with limited labeled data. We consider model initialization, diversity augmentation and pseudo-label editing simultaneously. In our work, we utilize output smearing to initialize modules, use fine-tuning on labeled data to augment diversity and eliminate unstable pseudo-labels to alleviate the influence of suspicious pseudo-labeled data. Experiments show that our method achieves the best performance in comparison with state-of-the-art semi-supervised deep learning methods. In particular, it achieves 8.30% error rate on CIFAR-10 by using only 4000 labeled examples.

A novel deep learning technique for analysis and detection of ARMD using OCT scan images

2021 ◽  
Vol 25 (3) ◽  
pp. 335-342
Author(s):  
P.V.G.D. Prasad Reddy
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Visual Imagery ◽  
Active Contour ◽  
Deep Neural Networks ◽  
Age Related Macular Degeneration ◽  
Age Related ◽  
Learning Technique ◽  
Medical Situation

Age-Related Macular Degeneration (ARMD) is a medical situation resulting in blurred or no vision in the middle of the eye view. Though this disease doesn’t make the person completely blind, it makes it very difficult for the person to perform day to day activities like reading, driving, recognizing people etc. This paper aims to detect ARMD though Optical Coherence Tomography (OCT) scans where the drusen in the macula is detected and identify the infected. The images are first passed though Directional Total Variation (DTV) Denoising followed by Active contour algorithm to mark the boundaries of the layers in macula. In deep learning, a convolutional neural network is a class of deep neural networks, most commonly applied to analyzing visual imagery. Then these images categorized as healthy and infected using Convolution Neural Network. Different CNN variant algorithms like Alexnet, VggNet and GoogleNet have been compared in the experiments and the results obtained are better compared to traditional methods.

Sign in / Sign up

Export Citation Format

Share Document