METRIC APPROACH TO SEMANTIC-MORPHOLOGICAL IMAGE COMPARISON

2020 ◽  
pp. 3-12
Author(s):  
Yu. V. Vizilter ◽  
O. V. Vygolov ◽  
S. Yu. Zheltov ◽  
V. V. Kniaz
Keyword(s):  
Deep Learning ◽  
Metric Space ◽  
Pairwise Comparison ◽  
Network Models ◽  
Parameter Tuning ◽  
Neural Network Models ◽  
Image Comparison ◽  
Feature Description ◽  
Estimation Scheme ◽  
The Individual

In this paper we propose and consider different metric approaches to image comparison based on Morpho-Semantic (MS) and Semantic-Morphological (SM) models. The first proposed class-based approach presumes the embedding of MS and SM models to the metric space with weighted Lp metrics. This approach is based on representation of SM models as mosaic vector functions composed of semantic-morphological class expression maps. The feature description of these maps provides a global feature description of SM models by SM vectors. The second proposed class-based approach is based on resource models, which include semantic-morphological class expression maps with area recourse values. This approach implements the embedding of these mosaic class expression maps with area recourse values to the metric space with Earth Mover’s Distance (EMD) based on resource transportation between these maps. Finally, we propose the object-based approach to metric embedding of SM models inspired by Geometrical Difference Distance (GDD), which performs the comparison of mosaic image shapes via weighted pairwise comparison of their region shapes. In this way we obtain the SM Difference Distance (SMDD) and its EMD-version (SMDD). The practical applicability of proposed SM-metrics is largely determined by the strategy of feature set forming and parameter estimation scheme. The SM-metrics parameter tuning for comparison of some visual scenes/objects could be performed both as MS-modeling (interpretation) of human subjective reasoning and as MS-modeling (interpretation) of deep learning results. In both cases, SM models and SM metrics fitting could allow: making partially transparent the human or DNN reasoning in scene comparison tasks; Comparing (grouping, clustering) different experts (algorithms) in terms of different parameters settings for SM-models; performing the personalized post-training of neural network models with taking into account the individual SM-settings of concrete users, operators or experts. This will combine the effectiveness of deep learning on huge training bases with partial transparency of reasoning and the possibility of directly taking into account the wishes of users in terms of SM-models, rather than by creating the artificial training bases via artificial augmentation.

Deep learning and complex network theory based analysis on socialized manufacturing resources utilisations and an application case study

2021 ◽  
pp. 1063293X2110031
Author(s):  
Maolin Yang ◽  
Auwal H Abubakar ◽  
Pingyu Jiang
Keyword(s):  
Deep Learning ◽  
Complex Network ◽  
Network Models ◽  
Neural Network Models ◽  
Complex Network Theory ◽  
New Type ◽  
Manufacturing Resource ◽  
Manufacturing Resources ◽  
Resource Characteristics

Social manufacturing is characterized by its capability of utilizing socialized manufacturing resources to achieve value adding. Recently, a new type of social manufacturing pattern emerges and shows potential for core factories to improve their limited manufacturing capabilities by utilizing the resources from outside socialized manufacturing resource communities. However, the core factories need to analyze the resource characteristics of the socialized resource communities before making operation plans, and this is challenging due to the unaffiliated and self-driven characteristics of the resource providers in socialized resource communities. In this paper, a deep learning and complex network based approach is established to address this challenge by using socialized designer community for demonstration. Firstly, convolutional neural network models are trained to identify the design resource characteristics of each socialized designer in designer community according to the interaction texts posted by the socialized designer on internet platforms. During the process, an iterative dataset labelling method is established to reduce the time cost for training set labelling. Secondly, complex networks are used to model the design resource characteristics of the community according to the resource characteristics of all the socialized designers in the community. Two real communities from RepRap 3D printer project are used as case study.

Feature extraction-based image steganalysis using deep learning

2021 ◽  
pp. 188-198
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Secure Communication ◽  
Information Technologies ◽  
Network Models ◽  
Error Rates ◽  
Multimedia Data ◽  
Secret Message ◽  
Neural Network Models

The innovations in advanced information technologies has led to rapid delivery and sharing of multimedia data like images and videos. The digital steganography offers ability to secure communication and imperative for internet. The image steganography is essential to preserve confidential information of security applications. The secret image is embedded within pixels. The embedding of secret message is done by applied with S-UNIWARD and WOW steganography. Hidden messages are reveled using steganalysis. The exploration of research interests focused on conventional fields and recent technological fields of steganalysis. This paper devises Convolutional neural network models for steganalysis. Convolutional neural network (CNN) is one of the most frequently used deep learning techniques. The Convolutional neural network is used to extract spatio-temporal information or features and classification. We have compared steganalysis outcome with AlexNet and SRNeT with same dataset. The stegnalytic error rates are compared with different payloads.

scholarly journals Deep Network Guided Proof Search

10.29007/8mwc ◽  
2018 ◽  
Author(s):  
Sarah Loos ◽  
Geoffrey Irving ◽  
Christian Szegedy ◽  
Cezary Kaliszyk
Keyword(s):  
Deep Learning ◽  
Program Analysis ◽  
Network Models ◽  
Theorem Prover ◽  
Neural Network Models ◽  
Two Phase ◽  
First Order ◽  
Proof Search ◽  
System Verification ◽  
Theory Reasoning

Deep learning techniques lie at the heart of several significant AI advances in recent years including object recognition and detection, image captioning, machine translation, speech recognition and synthesis, and playing the game of Go.Automated first-order theorem provers can aid in the formalization and verification of mathematical theorems and play a crucial role in program analysis, theory reasoning, security, interpolation, and system verification.Here we suggest deep learning based guidance in the proof search of the theorem prover E. We train and compare several deep neural network models on the traces of existing ATP proofs of Mizar statements and use them to select processed clauses during proof search. We give experimental evidence that with a hybrid, two-phase approach, deep learning based guidance can significantly reduce the average number of proof search steps while increasing the number of theorems proved.Using a few proof guidance strategies that leverage deep neural networks, we have found first-order proofs of 7.36% of the first-order logic translations of the Mizar Mathematical Library theorems that did not previously have ATP generated proofs. This increases the ratio of statements in the corpus with ATP generated proofs from 56% to 59%.

SEALing Neural Network Models in Encrypted Deep Learning Accelerators

2021 ◽  
Author(s):  
Pengfei Zuo ◽  
Yu Hua ◽  
Ling Liang ◽  
Xinfeng Xie ◽  
Xing Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Models ◽  
Neural Network Models

Bankruptcy Prediction Using Principal Component Analysis Based Neural Network Models

2010 ◽  
pp. 138-156
Author(s):  
G. A. Rekha Pai ◽  
G. A. Vijayalakshmi Pai
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Prediction Models ◽  
Network Models ◽  
Principal Component ◽  
Component Analysis ◽  
Bankruptcy Prediction ◽  
Financial Ratios ◽  
Neural Network Models ◽  
The Individual

Industrial bankruptcy is a rampant problem which does not occur overnight and when it occurs can cause acute financial embarrassment to Governments and financial institutions as well as threaten the very viability of the firms. It is therefore essential to help industries identify the impending trouble early. Several statistical and soft computing based bankruptcy prediction models that make use of financial ratios as indicators have been proposed. Majority of these models make use of a selective set of financial ratios chosen according to some appropriate criteria framed by the individual investigators. In contrast, this study considers any number of financial ratios irrespective of the industrial category and size and makes use of Principal Component Analysis to extract their principal components, to be used as predictors, thereby dispensing with the cumbersome selection procedures used by its predecessors. An Evolutionary Neural Network (ENN) and a Backpropagation Neural Network with Levenberg Marquardt’s training rule (BPN) have been employed as classifiers and their performance has been compared using Receiver Operating Characteristics (ROC) analyses. Termed PCA-ENN and PCA-BPN models, the predictive potential of the two models have been analyzed over a financial database (1997-2000) pertaining to 34 sick and 38 non sick Indian manufacturing companies, with 21 financial ratios as predictor variables.

scholarly journals Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps

2019 ◽  
Vol 1 (1) ◽  
pp. 450-465 ◽  
Author(s):  
Abhishek Sehgal ◽  
Nasser Kehtarnavaz
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Open Source Software ◽  
Mobile Applications ◽  
Network Models ◽  
Software Tools ◽  
Learning Tools ◽  
Smartphone Apps ◽  
Learning Models ◽  
Neural Network Models

Deep learning solutions are being increasingly used in mobile applications. Although there are many open-source software tools for the development of deep learning solutions, there are no guidelines in one place in a unified manner for using these tools toward real-time deployment of these solutions on smartphones. From the variety of available deep learning tools, the most suited ones are used in this paper to enable real-time deployment of deep learning inference networks on smartphones. A uniform flow of implementation is devised for both Android and iOS smartphones. The advantage of using multi-threading to achieve or improve real-time throughputs is also showcased. A benchmarking framework consisting of accuracy, CPU/GPU consumption, and real-time throughput is considered for validation purposes. The developed deployment approach allows deep learning models to be turned into real-time smartphone apps with ease based on publicly available deep learning and smartphone software tools. This approach is applied to six popular or representative convolutional neural network models, and the validation results based on the benchmarking metrics are reported.

Beluga whale acoustic signal classification using deep learning neural network models

2020 ◽  
Vol 147 (3) ◽  
pp. 1834-1841 ◽  
Author(s):  
Ming Zhong ◽  
Manuel Castellote ◽  
Rahul Dodhia ◽  
Juan Lavista Ferres ◽  
Mandy Keogh ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Acoustic Signal ◽  
Network Models ◽  
Beluga Whale ◽  
Signal Classification ◽  
Neural Network Models ◽  
Deep Learning Neural Network

Application of Deep Learning for Characterization of Drivers’ Engagement in Secondary Tasks in In-Vehicle Systems

2020 ◽  
Vol 2674 (8) ◽  
pp. 429-440
Author(s):  
Osama A. Osman ◽  
Hesham Rakha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Time Series Data ◽  
Short Term Memory ◽  
Network Models ◽  
Sensor Technology ◽  
Series Data ◽  
Neural Network Models ◽  
Secondary Tasks ◽  
Driving Assistance

Distracted driving (i.e., engaging in secondary tasks) is an epidemic that threatens the lives of thousands every year. Data collected from vehicular sensor technologies and through connectivity provide comprehensive information that, if used to detect driver engagement in secondary tasks, could save thousands of lives and millions of dollars. This study investigates the possibility of achieving this goal using promising deep learning tools. Specifically, two deep neural network models (a multilayer perceptron neural network model and a long short-term memory networks [LSTMN] model) were developed to identify three secondary tasks: cellphone calling, cellphone texting, and conversation with adjacent passengers. The Second Strategic Highway Research Program Naturalistic Driving Study (SHRP 2 NDS) time series data, collected using vehicle sensor technology, were used to train and test the model. The results show excellent performance for the developed models, with a slight improvement for the LSTMN model, with overall classification accuracies ranging between 95 and 96%. Specifically, the models are able to identify the different types of secondary tasks with high accuracies of 100% for calling, 96%–97% for texting, 90%–91% for conversation, and 95%–96% for the normal driving. Based on this performance, the developed models improve on the results of a previous model developed by the author to classify the same three secondary tasks, which had an accuracy of 82%. The model is promising for use in in-vehicle driving assistance technology to report engagement in unlawful tasks or alert drivers to take over control in level 1 and 2 automated vehicles.

A neural network model of the effects of entrenchment and memory development on grammatical gender learning

2012 ◽  
Vol 16 (2) ◽  
pp. 246-265 ◽  
Author(s):  
DEREK MONNER ◽  
KAREN VATZ ◽  
GIOVANNA MORINI ◽  
SO-ONE HWANG ◽  
ROBERT DeKEYSER
Keyword(s):  
Neural Network ◽  
Time Course ◽  
Age Of Onset ◽  
Network Models ◽  
Memory Development ◽  
Neural Network Models ◽  
Gender Assignment ◽  
Less Is More ◽  
Onset Delays ◽  
The Individual

To investigate potential causes of L2 performance deficits that correlate with age of onset, we use a computational model to explore the individual contributions of L1 entrenchment and aspects of memory development. Since development and L1 entrenchment almost invariably coincide, studying them independently is seldom possible in humans. To avoid this confound, we study neural network models that learn to solve gender assignment and agreement tasks in Spanish and French. We model the learner as a collection of recurrent cell assemblies that subserve working memory and are facilitated by trainable long-term connections. Varying the time-course over which assemblies and connections are added allows us to compare small, growing, child-like networks to fixed-size adult-like ones. Networks undergo variable-length exposure to L1 before L2 onset to control the amount of L1 entrenchment. This model, by allowing us independent control of both variables, lends us a novel glimpse of all sides of their interaction and affords a rare test of the less-is-more hypothesis. Network comparisons suggest that final L2 proficiency declines as L2 onset delays increase relative to L1, implicating an L1 entrenchment effect. However, aspects of memory development during learning play a key role in mitigating these impairments, lending support to less-is-more as a contributor to sensitive periods.

Sign in / Sign up

Export Citation Format

Share Document