scholarly journals Sensitivity Analysis of Deep Neural Networks

2019 ◽  
Vol 33 ◽  
pp. 4943-4950 ◽  
Author(s):  
Hai Shu ◽  
Hongtu Zhu
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Model Building ◽  
Information Geometry ◽  
Superior Performance ◽  
Invariance Properties ◽  
Influence Measure ◽  
Network Sensitivity ◽  
Adversarial Examples ◽  
Test Sets

Deep neural networks (DNNs) have achieved superior performance in various prediction tasks, but can be very vulnerable to adversarial examples or perturbations. Therefore, it is crucial to measure the sensitivity of DNNs to various forms of perturbations in real applications. We introduce a novel perturbation manifold and its associated influence measure to quantify the effects of various perturbations on DNN classifiers. Such perturbations include various external and internal perturbations to input samples and network parameters. The proposed measure is motivated by information geometry and provides desirable invariance properties. We demonstrate that our influence measure is useful for four model building tasks: detecting potential ‘outliers’, analyzing the sensitivity of model architectures, comparing network sensitivity between training and test sets, and locating vulnerable areas. Experiments show reasonably good performance of the proposed measure for the popular DNN models ResNet50 and DenseNet121 on CIFAR10 and MNIST datasets.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

scholarly journals Diversity Adversarial Training against Adversarial Attack on Deep Neural Networks

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 428
Author(s):  
Hyun Kwon ◽  
Jun Lee
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Diversity Training ◽  
Original Data ◽  
Training Method ◽  
Learning Framework ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Adversarial Attack ◽  
Accuracy Rates

This paper presents research focusing on visualization and pattern recognition based on computer science. Although deep neural networks demonstrate satisfactory performance regarding image and voice recognition, as well as pattern analysis and intrusion detection, they exhibit inferior performance towards adversarial examples. Noise introduction, to some degree, to the original data could lead adversarial examples to be misclassified by deep neural networks, even though they can still be deemed as normal by humans. In this paper, a robust diversity adversarial training method against adversarial attacks was demonstrated. In this approach, the target model is more robust to unknown adversarial examples, as it trains various adversarial samples. During the experiment, Tensorflow was employed as our deep learning framework, while MNIST and Fashion-MNIST were used as experimental datasets. Results revealed that the diversity training method has lowered the attack success rate by an average of 27.2 and 24.3% for various adversarial examples, while maintaining the 98.7 and 91.5% accuracy rates regarding the original data of MNIST and Fashion-MNIST.

scholarly journals Critical Assessment of Artificial Intelligence Methods for Prediction of hERG Channel Inhibition in the ‘Big Data’ Era

2020 ◽  
Author(s):  
Vishal Babu Siramshetty ◽  
Dac-Trung Nguyen ◽  
Natalia J. Martinez ◽  
Anton Simeonov ◽  
Noel T. Southall ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Big Data ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Prediction Models ◽  
Chemical Space ◽  
Superior Performance ◽  
Gradient Boosting ◽  
Artificial Intelligence Methods

The rise of novel artificial intelligence methods necessitates a comparison of this wave of new approaches with classical machine learning for a typical drug discovery project. Inhibition of the potassium ion channel, whose alpha subunit is encoded by human Ether-à-go-go-Related Gene (hERG), leads to prolonged QT interval of the cardiac action potential and is a significant safety pharmacology target for the development of new medicines. Several computational approaches have been employed to develop prediction models for assessment of hERG liabilities of small molecules including recent work using deep learning methods. Here we perform a comprehensive comparison of prediction models based on classical (random forests and gradient boosting) and modern (deep neural networks and recurrent neural networks) artificial intelligence methods. The training set (~9000 compounds) was compiled by integrating hERG bioactivity data from ChEMBL database with experimental data generated from an in-house, high-throughput thallium flux assay. We utilized different molecular descriptors including the latent descriptors, which are real-valued continuous vectors derived from chemical autoencoders trained on a large chemical space (> 1.5 million compounds). The models were prospectively validated on ~840 in-house compounds screened in the same thallium flux assay. The deep neural networks performed significantly better than the classical methods with the latent descriptors. The recurrent neural networks that operate on SMILES provided highest model sensitivity. The best models were merged into a consensus model that offered superior performance compared to reference models from academic and commercial domains. Further, we shed light on the potential of artificial intelligence methods to exploit the chemistry big data and generate novel chemical representations useful in predictive modeling and tailoring new chemical space.<br>

scholarly journals Prediction of Causative Genes in Inherited Retinal Disorders from Spectral-Domain Optical Coherence Tomography Utilizing Deep Learning Techniques

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Yu Fujinami-Yokokawa ◽  
Nikolas Pontikos ◽  
Lizhu Yang ◽  
Kazushige Tsunoda ◽  
Kazutoshi Yoshitake ◽  
...  
Keyword(s):  
Neural Networks ◽  
Optical Coherence Tomography ◽  
Classification Accuracy ◽  
Deep Neural Networks ◽  
Test Accuracy ◽  
Test Sets ◽  
The Mean ◽  
Per Gene ◽  
Sd Oct ◽  
Gene Category

Purpose. To illustrate a data-driven deep learning approach to predicting the gene responsible for the inherited retinal disorder (IRD) in macular dystrophy caused by ABCA4 and RP1L1 gene aberration in comparison with retinitis pigmentosa caused by EYS gene aberration and normal subjects. Methods. Seventy-five subjects with IRD or no ocular diseases have been ascertained from the database of Japan Eye Genetics Consortium; 10 ABCA4 retinopathy, 20 RP1L1 retinopathy, 28 EYS retinopathy, and 17 normal patients/subjects. Horizontal/vertical cross-sectional scans of optical coherence tomography (SD-OCT) at the central fovea were cropped/adjusted to a resolution of 400 pixels/inch with a size of 750 × 500 pix2 for learning. Subjects were randomly split following a 3 : 1 ratio into training and test sets. The commercially available learning tool, Medic mind was applied to this four-class classification program. The classification accuracy, sensitivity, and specificity were calculated during the learning process. This process was repeated four times with random assignment to training and test sets to control for selection bias. For each training/testing process, the classification accuracy was calculated per gene category. Results. A total of 178 images from 75 subjects were included in this study. The mean training accuracy was 98.5%, ranging from 90.6 to 100.0. The mean overall test accuracy was 90.9% (82.0–97.6). The mean test accuracy per gene category was 100% for ABCA4, 78.0% for RP1L1, 89.8% for EYS, and 93.4% for Normal. Test accuracy of RP1L1 and EYS was not high relative to the training accuracy which suggests overfitting. Conclusion. This study highlighted a novel application of deep neural networks in the prediction of the causative gene in IRD retinopathies from SD-OCT, with a high prediction accuracy. It is anticipated that deep neural networks will be integrated into general screening to support clinical/genetic diagnosis, as well as enrich the clinical education.

scholarly journals Inter-Class Angular Loss for Convolutional Neural Networks

2019 ◽  
Vol 33 ◽  
pp. 3894-3901 ◽  
Author(s):  
Le Hui ◽  
Xiang Li ◽  
Chen Gong ◽  
Meng Fang ◽  
Joey Tianyi Zhou ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
Learning Difficulties ◽  
Feature Space ◽  
Superior Performance ◽  
Strongly Correlated ◽  
Discriminative Ability ◽  
Practical Applications ◽  
Classification Tasks

Convolutional Neural Networks (CNNs) have shown great power in various classification tasks and have achieved remarkable results in practical applications. However, the distinct learning difficulties in discriminating different pairs of classes are largely ignored by the existing networks. For instance, in CIFAR-10 dataset, distinguishing cats from dogs is usually harder than distinguishing horses from ships. By carefully studying the behavior of CNN models in the training process, we observe that the confusion level of two classes is strongly correlated with their angular separability in the feature space. That is, the larger the inter-class angle is, the lower the confusion will be. Based on this observation, we propose a novel loss function dubbed “Inter-Class Angular Loss” (ICAL), which explicitly models the class correlation and can be directly applied to many existing deep networks. By minimizing the proposed ICAL, the networks can effectively discriminate the examples in similar classes by enlarging the angle between their corresponding class vectors. Thorough experimental results on a series of vision and nonvision datasets confirm that ICAL critically improves the discriminative ability of various representative deep neural networks and generates superior performance to the original networks with conventional softmax loss.

Sign in / Sign up

Export Citation Format

Share Document