scholarly journals Deep Learning for Abstract Argumentation Semantics

2020 ◽  
Author(s):  
Dennis Craandijk ◽  
Floris Bex
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Message Passing ◽  
Experimental Results ◽  
Basic Principles ◽  
Abstract Argumentation ◽  
Message Passing Algorithm

In this paper, we present a learning-based approach to determining acceptance of arguments under several abstract argumentation semantics. More specifically, we propose an argumentation graph neural network (AGNN) that learns a message-passing algorithm to predict the likelihood of an argument being accepted. The experimental results demonstrate that the AGNN can almost perfectly predict the acceptability under different semantics and scales well for larger argumentation frameworks. Furthermore, analysing the behaviour of the message-passing algorithm shows that the AGNN learns to adhere to basic principles of argument semantics as identified in the literature, and can thus be trained to predict extensions under the different semantics – we show how the latter can be done for multi-extension semantics by using AGNNs to guide a basic search. We publish our code at https://github.com/DennisCraandijk/DL-Abstract-Argumentation.

Matrix inference and estimation in multi-layer models*

2021 ◽  
Vol 2021 (12) ◽  
pp. 124004
Author(s):  
Parthe Pandit ◽  
Mojtaba Sahraee-Ardakan ◽  
Sundeep Rangan ◽  
Philip Schniter ◽  
Alyson K Fletcher
Keyword(s):  
Neural Network ◽  
Message Passing ◽  
Hidden Variables ◽  
Signal Recovery ◽  
Inference Problem ◽  
Neural Network Learning ◽  
Approximate Message Passing ◽  
Message Passing Algorithm ◽  
Training Samples ◽  
Mixed Regression

Abstract We consider the problem of estimating the input and hidden variables of a stochastic multi-layer neural network (NN) from an observation of the output. The hidden variables in each layer are represented as matrices with statistical interactions along both rows as well as columns. This problem applies to matrix imputation, signal recovery via deep generative prior models, multi-task and mixed regression, and learning certain classes of two-layer NNs. We extend a recently-developed algorithm—multi-layer vector approximate message passing, for this matrix-valued inference problem. It is shown that the performance of the proposed multi-layer matrix vector approximate message passing algorithm can be exactly predicted in a certain random large-system limit, where the dimensions N × d of the unknown quantities grow as N → ∞ with d fixed. In the two-layer neural-network learning problem, this scaling corresponds to the case where the number of input features as well as training samples grow to infinity but the number of hidden nodes stays fixed. The analysis enables a precise prediction of the parameter and test error of the learning.

scholarly journals Imbalance Modelling for Defect Detection in Ceramic Substrate by Using Convolutional Neural Network

Processes ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 1678
Author(s):  
Yo-Ping Huang ◽  
Chun-Ming Su ◽  
Haobijam Basanta ◽  
Yau-Liang Tsai
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Unsupervised Learning ◽  
Defect Detection ◽  
Ceramic Substrate ◽  
Experimental Results ◽  
Ceramic Substrates

The complexity of defect detection in a ceramic substrate causes interclass and intraclass imbalance problems. Identifying flaws in ceramic substrates has traditionally relied on aberrant material occurrences and characteristic quantities. However, defect substrates in ceramic are typically small and have a wide variety of defect distributions, thereby making defect detection more challenging and difficult. Thus, we propose a method for defect detection based on unsupervised learning and deep learning. First, the proposed method conducts K-means clustering for grouping instances according to their inherent complex characteristics. Second, the distribution of rarely occurring instances is balanced by using augmentation filters. Finally, a convolutional neural network is trained by using the balanced dataset. The effectiveness of the proposed method was validated by comparing the results with those of other methods. Experimental results show that the proposed method outperforms other methods.

scholarly journals CAPTCHA Recognition Using Deep Learning with Attached Binary Images

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1522
Author(s):  
Alaa Thobhani ◽  
Mingsheng Gao ◽  
Ammar Hawbani ◽  
Safwan Taher Mohammed Ali ◽  
Amr Abdussalam
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Character Recognition ◽  
Simple Structure ◽  
Experimental Results ◽  
End User ◽  
Binary Images ◽  
Storage Size ◽  
Specific Number

Websites can increase their security and prevent harmful Internet attacks by providing CAPTCHA verification for determining whether end-user is a human or a robot. Text-based CAPTCHA is the most common and designed to be easily recognized by humans and difficult to identify by machines or robots. However, with the dramatic advancements in deep learning, it becomes much easier to build convolutional neural network (CNN) models that can efficiently recognize text-based CAPTCHAs. In this study, we introduce an efficient CNN model that uses attached binary images to recognize CAPTCHAs. By making a specific number of copies of the input CAPTCHA image equal to the number of characters in that input CAPTCHA image and attaching distinct binary images to each copy, we build a new CNN model that can recognize CAPTCHAs effectively. The model has a simple structure and small storage size and does not require the segmentation of CAPTCHAs into individual characters. After training and testing the proposed CAPTCHA recognition CNN model, the achieved experimental results reveal the strength of the model in CAPTCHA character recognition.

scholarly journals Table Cleaning Task by Human Support Robot Using Deep Learning Technique

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1698 ◽  
Author(s):  
Jia Yin ◽  
Koppaka Ganesh Sai Apuroop ◽  
Yokhesh Krishnasamy Tamilselvam ◽  
Rajesh Elara Mohan ◽  
Balakrishnan Ramalingam ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Experimental Results ◽  
Detection Accuracy ◽  
Inspection Method ◽  
Learning Technique ◽  
Standard Quality ◽  
Typical Food ◽  
Human Support ◽  
Inspection Task

This work presents a table cleaning and inspection method using a Human Support Robot (HSR) which can operate in a typical food court setting. The HSR is able to perform a cleanliness inspection and also clean the food litter on the table by implementing a deep learning technique and planner framework. A lightweight Deep Convolutional Neural Network (DCNN) has been proposed to recognize the food litter on top of the table. In addition, the planner framework was proposed to HSR for accomplishing the table cleaning task which generates the cleaning path according to the detection of food litter and then the cleaning action is carried out. The effectiveness of the food litter detection module is verified with the cleanliness inspection task using Toyota HSR, and its detection results are verified with standard quality metrics. The experimental results show that the food litter detection module achieves an average of 96 % detection accuracy, which is more suitable for deploying the HSR robots for performing the cleanliness inspection and also helps to select the different cleaning modes. Further, the planner part has been tested through the table cleaning tasks. The experimental results show that the planner generated the cleaning path in real time and its generated path is optimal which reduces the cleaning time by grouping based cleaning action for removing the food litters from the table.

scholarly journals Global and Local Attention-Based Free-Form Image Inpainting

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3204
Author(s):  
S. M. Nadim Uddin ◽  
Yong Ju Jung
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Image Inpainting ◽  
Experimental Results ◽  
Free Form ◽  
Local Similarity ◽  
Global And Local ◽  
Similarity Information

Deep-learning-based image inpainting methods have shown significant promise in both rectangular and irregular holes. However, the inpainting of irregular holes presents numerous challenges owing to uncertainties in their shapes and locations. When depending solely on convolutional neural network (CNN) or adversarial supervision, plausible inpainting results cannot be guaranteed because irregular holes need attention-based guidance for retrieving information for content generation. In this paper, we propose two new attention mechanisms, namely a mask pruning-based global attention module and a global and local attention module to obtain global dependency information and the local similarity information among the features for refined results. The proposed method is evaluated using state-of-the-art methods, and the experimental results show that our method outperforms the existing methods in both quantitative and qualitative measures.

scholarly journals Better Effectiveness of Multi-Integrated Neural Networks: Take Stock Big Data as an Example

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
HangLin Lu ◽  
XiuYun Peng
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Deep Learning ◽  
High Latitude ◽  
Integrated Model ◽  
Experimental Results ◽  
Single Model ◽  
Integration Model ◽  
Model Based ◽  
Better Than

With the development of big data, in the financial market, the stock price prediction has many research directions from the perspective of big data. The classical time series prediction model cannot adapt to the high-latitude information of stock data in the era of big data. The development of deep learning provides a new idea for high-latitude stock data prediction. Four neural network models and three integrated learning models form different strategy sets, and the opening price of the next timestamp is predicted by backtracking information over the past 15 days with the characteristics of 12 indexes of the stock. The experimental results show that the prediction effect of the integration model based on the average weight policy and stacking policy is better than that of the single neural network, and the integration model based on stacking policy is expected to have the highest prediction accuracy and the minimum expected error. The accuracy was 80.2%, and the mean square error was 0.024. Compared with the single model, the accuracy is increased by 2%~7%, and the error is reduced by 0.01~0.03. The innovation of this article lies in the traditional machine learning thinking is applied to deep learning, as an individual with a variety of neural network to study, through the integration of learning strategies, fusion for the integration model, the experimental results show that the effect of the integrated model is better than that of a single model, to improve the robustness and accuracy of the model; the performance of the integrated model is more stable. For the utilization of big data resources, the integrated model of neural network has better prediction effect.

Development of Deep Learning Framework for Mathematical Morphology

2019 ◽  
Vol 33 (06) ◽  
pp. 1954024 ◽  
Author(s):  
Frank Y. Shih ◽  
Yucong Shen ◽  
Xin Zhong
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Mathematical Morphology ◽  
Experimental Results ◽  
Morphological Operations ◽  
Learning Framework ◽  
Structuring Element ◽  
The Neural Network ◽  
Object Features

Mathematical morphology has been applied as a collection of nonlinear operations related to object features in images. In this paper, we present morphological layers in deep learning framework, namely MorphNet, to perform atomic morphological operations, such as dilation and erosion. For propagation of losses through the proposed deep learning framework, we approximate the dilation and erosion operations by differential and smooth multivariable functions of the softmax function, and therefore enable the neural network to be optimized. The proposed operations are analyzed by the derivative of approximation functions in the deep learning framework. Experimental results show that the output structuring element of a morphological neuron and the target structuring element are matched to confirm the efficiency and correctness of the proposed framework.

scholarly journals Applying Visual Cryptography to Enhance Text Captchas

Mathematics ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 332
Author(s):  
Xuehu Yan ◽  
Feng Liu ◽  
Wei Qi Yan ◽  
Yuliang Lu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Recognition Rate ◽  
Visual Cryptography ◽  
Experimental Results ◽  
Authentication Mechanism ◽  
Human Eyes ◽  
Attack Models

Nowadays, lots of applications and websites utilize text-based captchas to partially protect the authentication mechanism. However, in recent years, different ways have been exploited to automatically recognize text-based captchas especially deep learning-based ways, such as, convolutional neural network (CNN). Thus, we have to enhance the text captchas design. In this paper, using the features of the randomness for each encoding process in visual cryptography (VC) and the visual recognizability with naked human eyes, VC is applied to design and enhance text-based captcha. Experimental results using two typical deep learning-based attack models indicate the effectiveness of the designed method. By using our designed VC-enhanced text-based captcha (VCETC), the recognition rate is in some degree decreased.

Sign in / Sign up

Export Citation Format

Share Document