scholarly journals Improving Neural Network Verification through Spurious Region Guided Refinement

2021 ◽  
pp. 389-408
Author(s):  
Pengfei Yang ◽  
Renjue Li ◽  
Jianlin Li ◽  
Cheng-Chao Huang ◽  
Jingyi Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Programming ◽  
Experimental Results ◽  
Abstraction Refinement ◽  
Robustness Property ◽  
The Core ◽  
Programming Techniques ◽  
Core Idea ◽  
Network Verification

AbstractWe propose a spurious region guided refinement approach for robustness verification of deep neural networks. Our method starts with applying the DeepPoly abstract domain to analyze the network. If the robustness property cannot be verified, the result is inconclusive. Due to the over-approximation, the computed region in the abstraction may be spurious in the sense that it does not contain any true counterexample. Our goal is to identify such spurious regions and use them to guide the abstraction refinement. The core idea is to make use of the obtained constraints of the abstraction to infer new bounds for the neurons. This is achieved by linear programming techniques. With the new bounds, we iteratively apply DeepPoly, aiming to eliminate spurious regions. We have implemented our approach in a prototypical tool DeepSRGR. Experimental results show that a large amount of regions can be identified as spurious, and as a result, the precision of DeepPoly can be significantly improved. As a side contribution, we show that our approach can be applied to verify quantitative robustness properties.

scholarly journals DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis

2021 ◽  
Author(s):  
Patrick Henriksen ◽  
Alessio Lomuscio
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Linear Programming ◽  
Indirect Effect ◽  
Splitting Method ◽  
New Method ◽  
Effect Analysis ◽  
Feed Forward ◽  
Network Verification

We propose a novel, complete algorithm for the verification and analysis of feed-forward, ReLU-based neural networks. The algorithm, based on symbolic interval propagation, introduces a new method for determining split-nodes which evaluates the indirect effect that splitting has on the relaxations of successor nodes. We combine this with a new efficient linear-programming encoding of the splitting constraints to further improve the algorithm’s performance. The resulting implementation, DeepSplit, achieved speedups of 1–2 orders of magnitude and 21-34% fewer timeouts when compared to the current SoA toolkits.

scholarly journals Convolutional Neural Networks for Leaf Image-Based Plant Disease Classification

2019 ◽  
Vol 8 (4) ◽  
pp. 328
Author(s):  
Sachin B. Jadhav
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Plant Diseases ◽  
Experimental Results ◽  
Disease Classification ◽  
Soybean Leaves ◽  
Soybean Diseases ◽  
Validation Strategy

<span lang="EN-US">Plant pathologists desire soft computing technology for accurate and reliable diagnosis of plant diseases. In this study, we propose an efficient soybean disease identification method based on a transfer learning approach by using a pre-trained convolutional neural network (CNN’s) such as AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201. The proposed convolutional neural networks were trained using 1200 plant village image dataset of diseased and healthy soybean leaves, to identify three soybean diseases out of healthy leaves. Pre-trained CNN used to enable a fast and easy system implementation in practice. We used the five-fold cross-validation strategy to analyze the performance of networks. In this study, we used a pre-trained convolutional neural network as feature extractors and classifiers. The experimental results based on the proposed approach using pre-trained AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201 networks achieve an accuracy of 95%, 96.4 %, 96.4 %, 92.1%, 93.6% respectively. The experimental results for the identification of soybean diseases indicated that the proposed networks model achieves the highest accuracy</span>

scholarly journals Investigation of optimal configurations of a convolutional neural network for the identification of objects in real-time

2019 ◽  
pp. 417-423
Author(s):  
M A Isayev ◽  
D A Savelyev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Real Time ◽  
State Of The Art ◽  
Average Precision ◽  
The Core ◽  
Particular Solution ◽  
Optimal Configurations

The comparison of different convolutional neural networks which are the core of the most actual solutions in the computer vision area is considers in hhe paper. The study includes benchmarks of this state-of-the-art solutions by some criteria, such as mAP (mean average precision), FPS (frames per seconds), for the possibility of real-time usability. It is concluded on the best convolutional neural network model and deep learning methods that were used at particular solution.

scholarly journals PREDETERMINED MOVEMENT OF MOBILE ROBOT USING NEURAL NETWORKS

2014 ◽  
pp. 64-68
Author(s):  
Oleh Adamiv ◽  
Vasyl Koval ◽  
Iryna Turchenko
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mobile Robot ◽  
Formation Process ◽  
Robot Control ◽  
Experimental Results ◽  
The Road ◽  
Mobile Robot Control ◽  
Different Parts ◽  
Training Sets

This paper describes the experimental results of neural networks application for mobile robot control on predetermined trajectory of the road. There is considered the formation process of training sets for neural network, their structure and simulating features. Researches have showed robust mobile robot movement on different parts of the road.

Contributions to Ranking an Ergonomic Workstation, Considering the Human Effort and the Microclimate Parameters, Using Neural Networks

2013 ◽  
Vol 371 ◽  
pp. 812-816 ◽  
Author(s):  
Daniel Constantin Anghel ◽  
Nadia Belu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Experimental Results ◽  
Work Place ◽  
Feed Forward Neural Network ◽  
Linear Relationships ◽  
The Neural Network ◽  
Manufacture Industry ◽  
Human Effort ◽  
Hidden Layer

The paper presents a method to use a feed forward neural network in order to rank a working place from the manufacture industry. Neural networks excel in gathering difficult non-linear relationships between the inputs and outputs of a system. The neural network is simulated with a simple simulator: SSNN. In this paper, we considered as relevant for a work place ranking, 6 input parameters: temperature, humidity, noise, luminosity, load and frequency. The neural network designed for the study presented in this paper has 6 input neurons, 13 neurons in the hidden layer and 1 neuron in the output layer. We present also some experimental results obtained through simulations.

scholarly journals Novel Convolutional Neural Network with Variational Information Bottleneck for P300 Detection

Entropy ◽  
2020 ◽  
Vol 23 (1) ◽  
pp. 39
Author(s):  
Hongpeng Liao ◽  
Jianwu Xu ◽  
Zhuliang Yu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Character Recognition ◽  
Signal To Noise Ratio ◽  
Recognition Performance ◽  
Experimental Results ◽  
Redundant Information ◽  
Promising Tool ◽  
Information Bottleneck

In the area of brain-computer interfaces (BCI), the detection of P300 is a very important technique and has a lot of applications. Although this problem has been studied for decades, it is still a tough problem in electroencephalography (EEG) signal processing owing to its high dimension features and low signal-to-noise ratio (SNR). Recently, neural networks, like conventional neural networks (CNN), has shown excellent performance on many applications. However, standard convolutional neural networks suffer from performance degradation on dealing with noisy data or data with too many redundant information. In this paper, we proposed a novel convolutional neural network with variational information bottleneck for P300 detection. Wiht the CNN architecture and information bottleneck, the proposed network termed P300-VIB-Net could remove the redundant information in data effectively. The experimental results on BCI competition data sets show that P300-VIB-Net achieves cutting-edge character recognition performance. Furthermore, the proposed model is capable of restricting the flow of irrelevant information adaptively in the network from perspective of information theory. The experimental results show that P300-VIB-Net is a promising tool for P300 detection.

scholarly journals Using Attenuation Coefficient Generating Function in Parallel Execution of Neural Networks for Solving SAT

2005 ◽  
Vol 9 (2) ◽  
pp. 121-126 ◽  
Author(s):  
Kairong Zhang ◽  
◽  
Masahiro Nagamatu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Probability Density Function ◽  
Attenuation Coefficient ◽  
Parallel Execution ◽  
Experimental Results ◽  
Attenuation Coefficients ◽  
Execution Speed ◽  
Speedup Ratio ◽  
Analog Neural Network

The satisfiability problem (SAT) is one of the most basic and important problems in computer science. We have proposed a recurrent analog neural network called Lagrange Programming neural network with Polarized High-order connections (LPPH) for the SAT, together with a method of parallel execution of LPPH. Experimental results demonstrate a high speedup ratio. Furthermore this method is very easy to realize by hardware. LPPH dynamics has an important parameter, the attenuation coefficient, known to strongly affect LPPH execution speed, but determining a good value of attenuation coefficient is difficult. Experimental results show that the parallel execution reduces this difficulty. In this paper we propose a method to assign different values of attenuation coefficients to LPPHs used in the parallel execution. The values are generated uniformly randomly or randomly using a probability density function.

scholarly journals GSN: A Graph-Structured Network for Multi-Party Dialogues

2019 ◽  
Author(s):  
Wenpeng Hu ◽  
Zhangming Chan ◽  
Bing Liu ◽  
Dongyan Zhao ◽  
Jinwen Ma ◽  
...  
Keyword(s):  
Neural Network ◽  
Information Flow ◽  
Real World ◽  
Experimental Results ◽  
Neural Models ◽  
The Core ◽  
Dialogue Modeling ◽  
Special Case

Existing neural models for dialogue response generation assume that utterances are sequentially organized. However, many real-world dialogues involve multiple interlocutors (i.e., multi-party dialogues), where the assumption does not hold as utterances from different interlocutors can occur ``in parallel.'' This paper generalizes existing sequence-based models to a Graph-Structured neural Network (GSN) for dialogue modeling. The core of GSN is a graph-based encoder that can model the information flow along the graph-structured dialogues (two-party sequential dialogues are a special case). Experimental results show that GSN significantly outperforms existing sequence-based models.

scholarly journals A study of supervised combined neural-network-based ultrasonic method for reconstruction of spatial distribution of material properties

2020 ◽  
Vol 49 (3) ◽  
pp. 381-394
Author(s):  
Paulius Dapkus ◽  
Liudas Mažeika ◽  
Vytautas Sliesoraitis
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Grain Size ◽  
Ultrasonic Method ◽  
Size Estimation ◽  
Estimation Model ◽  
Robustness Property ◽  
Object Structure ◽  
Fully Connected ◽  
Grain Size Estimation

This paper examines the performance of the commonly used neural-network-based classifiers for investigating a structural noise in metals as grain size estimation. The biggest problem which aims to identify the object structure grain size based on metal features or the object structure itself. When the structure data is obtained, a proposed feature extraction method is used to extract the feature of the object. Afterwards, the extracted features are used as the inputs for the classifiers. This research studies is focused to use basic ultrasonic sensors to obtain objects structural grain size which are used in neural network. The performance for used neural-network-based classifier is evaluated based on recognition accuracy for individual object. Also, traditional neural networks, namely convolutions and fully connected dense networks are shown as a result of grain size estimation model. To evaluate robustness property of neural networks, the original samples data is mixed for three types of grain sizes. Experimental results show that combined convolutions and fully connected dense neural networks with classifiers outperform the others single neural networks with original samples with high SN data. The Dense neural network as itself demonstrates the best robustness property when the object samples not differ from trained datasets.

Sign in / Sign up

Export Citation Format

Share Document