scholarly journals Formal Proofs of Orthogonality for Class-Incremental Learning for Wireless Device Identification in IoT

2021 ◽  
Author(s):  
Yongxin Liu ◽  
Jian Wang ◽  
Jianqiang Li ◽  
Shuteng Niu ◽  
Houbing Song
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Incremental Learning ◽  
Learning Algorithm ◽  
Formal Proof ◽  
Formal Proofs ◽  
Device Identification ◽  
Wireless Device ◽  
Channel Separation ◽  
Approximate Orthogonality

<div> <div> <div> <p>This document provides a formal proof and supple- mentary information of the paper: Class-Incremental Learning for Wireless Device Identification in IoT. The original paper focuses on providing a novel and efficient incremental learning algorithm. In this document, we explicitly explain why the mem- ory representations (latent device fingerprints in our application) in Artificial Neural Networks approximate orthogonality with insights for the invention of our Channel Separation Incremental Learning algorithm. </p> </div> </div> </div>

scholarly journals Formal Proofs of Orthogonality for Class-Incremental Learning for Wireless Device Identification in IoT

2021 ◽  
Author(s):  
Yongxin Liu ◽  
Jian Wang ◽  
Jianqiang Li ◽  
Shuteng Niu ◽  
Houbing Song
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Incremental Learning ◽  
Learning Algorithm ◽  
Formal Proof ◽  
Formal Proofs ◽  
Device Identification ◽  
Wireless Device ◽  
Channel Separation ◽  
Approximate Orthogonality

<div> <div> <div> <p>This document provides a formal proof and supple- mentary information of the paper: Class-Incremental Learning for Wireless Device Identification in IoT. The original paper focuses on providing a novel and efficient incremental learning algorithm. In this document, we explicitly explain why the mem- ory representations (latent device fingerprints in our application) in Artificial Neural Networks approximate orthogonality with insights for the invention of our Channel Separation Incremental Learning algorithm. </p> </div> </div> </div>

scholarly journals Implementation of Incremental Learning in Artificial Neural Networks

10.29007/8559 ◽  
2018 ◽  
Author(s):  
Mariela Andrade ◽  
Eduardo Gasca ◽  
Eréndira Rendón
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Incremental Learning ◽  
Learning Algorithm ◽  
Human Memory ◽  
Support Vector ◽  
Training Set ◽  
New Knowledge ◽  
Target Network ◽  
Artificial Neural

Nowadays, the use of artificial neural networks (ANN), in particular the Multilayer Perceptron (MLP), is very popular for executing different tasks such as pattern recognition, data mining, and process automation. However, there are still weaknesses in these models when compared with human capabilities. A characteristic of human memory is the ability for learning new concepts without forgetting what we learned in the past, which has been a disadvantage in the field of artificial neural networks. How can we add new knowledge to the network without forgetting what has already been learned, without repeating the exhaustive ANN process? In an exhaustively training is used a complete training set, with all objects of all classes.In this work, we present a novel incremental learning algorithm for the MLP. New knowledge is incorporated into the target network without executing an exhaustive retraining. Objects of a new class integrate this knowledge, which was not included in the training of a source network. The algorithm consists in taking the final weights from the source network, doing a correction of these with the Support Vector Machine tools, and transferring the obtained weights to a target network. This last net is trained with a training set that it is previously preprocessed. The efficiency resulted of the target network is comparable with a net that is exhaustively trained.

Sliding mode incremental learning algorithm for interval type-2 Takagi–Sugeno–Kang fuzzy neural networks

2012 ◽  
Vol 3 (3) ◽  
pp. 179-188 ◽  
Author(s):  
Sevil Ahmed ◽  
Nikola Shakev ◽  
Andon Topalov ◽  
Kostadin Shiev ◽  
Okyay Kaynak
Keyword(s):  
Neural Networks ◽  
Incremental Learning ◽  
Sliding Mode ◽  
Learning Algorithm ◽  
Fuzzy Neural Networks ◽  
Fuzzy Neural ◽  
Interval Type ◽  
Takagi Sugeno

Web tension control of multispan roll-to-roll system by artificial neural networks for printed electronics

2013 ◽  
Vol 227 (10) ◽  
pp. 2361-2376 ◽  
Author(s):  
KyungHyun Choi ◽  
Muhammad Zubair ◽  
Ganeshthangaraj Ponniah
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Printed Electronics ◽  
Learning Algorithm ◽  
Network Control ◽  
Learning Rate ◽  
Roll To Roll ◽  
Roll System ◽  
Artificial Neural ◽  
Web Tension

The mass production of printed electronic devices can be achieved by roll-to-roll system that requires highly regulated web tension. This highly regulated tension is required to minimize printing register error and maintain proper roughness and thickness of the printed patterns. The roll-to-roll system has a continuous changing roll diameter and a strong coupling exists between the spans. The roll-to-roll system is a multi-input-multi-output, time variant, and nonlinear system. The conventional proportional–integral–derivative control, used in industry, is not able to cope with roll-to-roll system for printed electronics. In this study, multi-input-single-output decentralized control scheme is used for control of a multispan roll-to-roll system by applying regularized variable learning rate backpropagating artificial neural networks. Additional inputs from coupled spans are given to regularized variable learning rate backpropagating artificial neural network control to decouple the two spans. Experimental results show that the self-learning algorithm offers a solution to decouple speed and tension in a multispan roll-to-roll system.

Volume Learning Algorithm Artificial Neural Networks for 3D QSAR Studies

2001 ◽  
Vol 44 (15) ◽  
pp. 2411-2420 ◽  
Author(s):  
Igor V. Tetko ◽  
Vasyl V. Kovalishyn ◽  
David J. Livingstone
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Learning Algorithm ◽  
3D Qsar ◽  
Qsar Studies ◽  
Artificial Neural

scholarly journals Diagnosing Diabetes Using Artificial Neural Networks

2020 ◽  
Vol 5 (2) ◽  
pp. 221-224
Author(s):  
Joy Oyinye Orukwo ◽  
Ledisi Giok Kabari
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Success Rate ◽  
Medical Diagnosis ◽  
Learning Algorithm ◽  
Diabetes Diagnosis ◽  
Feed Forward Neural Network ◽  
The Neural Network ◽  
Artificial Neural

Diabetes has always been a silent killer and the number of people suffering from it has increased tremendously in the last few decades. More often than not, people continue with their normal lifestyle, unaware that their health is at severe risk and with each passing day diabetes goes undetected. Artificial Neural Networks have become extensively useful in medical diagnosis as it provides a powerful tool to help analyze, model and make sense of complex clinical data. This study developed a diabetes diagnosis system using feed-forward neural network with supervised learning algorithm. The neural network is systematically trained and tested and a success rate of 90% was achieved.

Sign in / Sign up

Export Citation Format

Share Document