A GA-Based Pruning Fully Connected Network for Tuned Connections in Deep Networks

2019 ◽  
Author(s):  
Amin Khatami ◽  
Parham M. Kebria ◽  
Seyed Mohammad Jafar Jalali ◽  
Abbas Khosravi ◽  
Asef Nazari ◽  
...  
Keyword(s):  
Connected Network ◽  
Deep Networks ◽  
Fully Connected

scholarly journals Fully connected network of superconducting qubits in a cavity

2008 ◽  
Vol 10 (11) ◽  
pp. 113020 ◽  
Author(s):  
Dimitris I Tsomokos ◽  
Sahel Ashhab ◽  
Franco Nori
Keyword(s):  
Superconducting Qubits ◽  
Connected Network ◽  
Fully Connected

scholarly journals Investigasi Pengaruh Skema Stride dan Step Training untuk Deteksi Jari Pada Region-based Fully Convolutional Network (R-FCN) dalam Teknologi Augmented Reality

2021 ◽  
Vol 12 (2) ◽  
pp. 138
Author(s):  
Hashfi Fadhillah ◽  
Suryo Adhi Wibowo ◽  
Rita Purnamasari
Keyword(s):  
Deep Learning ◽  
Augmented Reality ◽  
Virtual World ◽  
Training Data ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Connected Network ◽  
Learning Region ◽  
Centroid Point ◽  
Fully Connected

Abstract  Combining the real world with the virtual world and then modeling it in 3D is an effort carried on Augmented Reality (AR) technology. Using fingers for computer operations on multi-devices makes the system more interactive. Marker-based AR is one type of AR that uses markers in its detection. This study designed the AR system by detecting fingertips as markers. This system is designed using the Region-based Deep Fully Convolutional Network (R-FCN) deep learning method. This method develops detection results obtained from the Fully Connected Network (FCN). Detection results will be integrated with a computer pointer for basic operations. This study uses a predetermined step scheme to get the best IoU parameters, precision and accuracy. The scheme in this study uses a step scheme, namely: 25K, 50K and 75K step. High precision creates centroid point changes that are not too far away. High accuracy can improve AR performance under conditions of rapid movement and improper finger conditions. The system design uses a dataset in the form of an index finger image with a configuration of 10,800 training data and 3,600 test data. The model will be tested on each scheme using video at different distances, locations and times. This study produced the best results on the 25K step scheme with IoU of 69%, precision of 5.56 and accuracy of 96%.Keyword: Augmented Reality, Region-based Convolutional Network, Fully Convolutional Network, Pointer, Step training Abstrak Menggabungkan dunia nyata dengan dunia virtual lalu memodelkannya bentuk 3D merupakan upaya yang diusung pada teknologi Augmented Reality (AR). Menggunakan jari untuk operasi komputer pada multi-device membuat sistem yang lebih interaktif. Marker-based AR merupakan salah satu jenis AR yang menggunakan marker dalam deteksinya. Penelitian ini merancang sistem AR dengan mendeteksi ujung jari sebagai marker. Sistem ini dirancang menggunakan metode deep learning Region-based Fully Convolutional Network (R-FCN). Metode ini mengembangkan hasil deteksi yang didapat dari Fully Connected Network (FCN). Hasil deteksi akan diintegrasikan dengan pointer komputer untuk operasi dasar. Penelitian ini menggunakan skema step training yang telah ditentukan untuk mendapatkan parameter IoU, presisi dan akurasi yang terbaik. Skema pada penelitian ini menggunakan skema step yaitu: 25K, 50K dan 75K step. Presisi tinggi menciptakan perubahan titik centroid yang tidak terlalu jauh. Akurasi  yang tinggi dapat meningkatkan kinerja AR dalam kondisi pergerakan yang cepat dan kondisi jari yang tidak tepat. Perancangan sistem menggunakan dataset berupa citra jari telunjuk dengan konfigurasi 10.800 data latih dan 3.600 data uji. Model akan diuji pada tiap skema dilakukan menggunakan video pada jarak, lokasi dan waktu yang berbeda. Penelitian ini menghasilkan hasil terbaik pada skema step 25K dengan IoU sebesar 69%, presisi sebesar 5,56 dan akurasi sebesar 96%.Kata kunci: Augmented Reality, Region-based Convolutional Network, Fully Convolutional Network, Pointer, Step training 

LEARNING ATTRACTOR NEURAL NETWORK: THE ELECTRONIC IMPLEMENTATION

1992 ◽  
Vol 03 (supp01) ◽  
pp. 13-24 ◽  
Author(s):  
Davide Badoni ◽  
Roberto Riccardi ◽  
Gaetano Salina
Keyword(s):  
Neural Network ◽  
Connected Network ◽  
Fully Connected ◽  
Electronic Implementation

In this article we describe the electronic implementation of an attractor neural network with plastic analog synapses. The project for a 27 neurons fully connected network will be shown together with the most important electronic tests we have carried out on a smaller network.

scholarly journals Security of search and verification protocol in multidimensional blockchain

2021 ◽  
Vol 20 (4) ◽  
pp. 793-819
Author(s):  
Ilya Shilov ◽  
Danil Zakoldaev
Keyword(s):  
Connected Graph ◽  
Data Exchange ◽  
Security Evaluation ◽  
Network Graph ◽  
Connected Network ◽  
Subset Principle ◽  
Speed Up ◽  
Evaluation Of Data ◽  
Fully Connected ◽  
Verification Techniques

The issue of secure data exchange and performing external transactions between robust distributed ledgers has recently been among the most significant in the sphere of designing and implementing decentralized technologies. Several approaches have been proposed to speed up the process of verifying transactions on adjacent blockchains. The problem of search has not been under research yet. The paper contains security evaluation of data exchange between independent robust distributed ledgers inside multidimensional blockchain. Main principles, basic steps of the protocol and major requirements for it are observed: centralized approach, subset principle and robust SVP. An equivalence of centralized approach and ideal search and verification functionality is proven. The probability of successful verification in case of using fully connected network graph or equivalent approach with fully connected graph between parent and child blockchain is shown. The insecurity of approach with one-to-one links between child and parent ledgers or with a subset principle is proven. A robust search and verification protocol for blocks and transactions based on the features of robust distributed ledgers is presented. The probability of attack on this protocol is mostly defined by the probability of attack on verification and not on search. An approach to protection against an attacker with 50% of nodes in the network is given. It is based on combination of various search and verification techniques.

Sign in / Sign up

Export Citation Format

Share Document