Adaptive Algorithms for Neural Network Supervised Learning: A Deterministic Optimization Approach

Magoulas, George D.; Vrahatis, Michael N.

doi:10.1142/s0218127406015805

Cited by 20 publications

(11 citation statements)

References 78 publications

(136 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since ANNs traditionally learn internal representations by adjusting the weights of the network connections, the inclusion of an adaptive algorithm improves learning by retropropagation through non-linear optimisation theory. This approach is useful when the learning process of an ANN is affected by accuracy flaws in the numerical computation, and environmental changes that cause unpredictable deviations of the parameter values from the original configuration [ 83 ].…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review

Vélez-Guerrero

Callejas-Cuervo

Mazzoleni

2021

Sensors

View full text Add to dashboard Cite

Processing and control systems based on artificial intelligence (AI) have progressively improved mobile robotic exoskeletons used in upper-limb motor rehabilitation. This systematic review presents the advances and trends of those technologies. A literature search was performed in Scopus, IEEE Xplore, Web of Science, and PubMed using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology with three main inclusion criteria: (a) motor or neuromotor rehabilitation for upper limbs, (b) mobile robotic exoskeletons, and (c) AI. The period under investigation spanned from 2016 to 2020, resulting in 30 articles that met the criteria. The literature showed the use of artificial neural networks (40%), adaptive algorithms (20%), and other mixed AI techniques (40%). Additionally, it was found that in only 16% of the articles, developments focused on neuromotor rehabilitation. The main trend in the research is the development of wearable robotic exoskeletons (53%) and the fusion of data collected from multiple sensors that enrich the training of intelligent algorithms. There is a latent need to develop more reliable systems through clinical validation and improvement of technical characteristics, such as weight/dimensions of devices, in order to have positive impacts on the rehabilitation process and improve the interactions among patients, teams of health professionals, and technology.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review

Vélez-Guerrero

Callejas-Cuervo

Mazzoleni

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…With the large-scale acceptance ANNs as e±cient feature extractors, it has been applied to¯elds like occupational stress analysis and prediction 27 and prediction of inside air temperature of pillar coolers based on parameters like outside temperature, watering, and airing. 28 Neural networks depend on various factors for getting good classi¯cation results, 29 one of the most important factors being the training algorithm used to train the network. Choosing the best suited and optimized training algorithm for training the network is a crucial step since it a®ects the time required to train the model, its accuracy, precision, and requirement of computing power.…”

Section: Related Workmentioning

confidence: 99%

A Framework for Selection of Training Algorithm of Neuro-Statistic Model for Prediction of Pig Breeds in India

Mandal

Ghosh

Shit

et al. 2020

Vietnam J. Comp. Sci.

View full text Add to dashboard Cite

Various training algorithms are used in artificial neural networks for updating the weights during training the network. But, the selection of the appropriate training algorithm is dependent on the input–output mapping of dataset for which the network is constructed. In this paper, a framework has been proposed consisting of five modules to select the optimal training algorithm for predicting pig breeds from their images. The individual pig images from five pig-breeds have been captured using inbuilt camera of mobile phone and the contour of pig has been segmented from each captured image by HUE-based segmentation algorithm. In Statistical Parameter and Color Component retrieval module, parameters like entropy, standard deviation, variance, mean, median, and mode and color properties like hue, saturation, value (HSV) extracted from the content of each segmented image. Values of all extracted parameters have been transferred into Training Algorithm Selection Module. In this module, a fitting neural network with different numbers of hidden neurons has been executed by feeding all extracted values from pig images for mapping their breeds. Ten training algorithms have been applied on the same extracted dataset separately for five epochs each keeping other network parameters constants. The mean square error (MSE) and correlation coefficient ([Formula: see text]) for the validation set have been calculated after adjustment of weights and biases in each connection of the neurons. One training algorithm among 10 and its suitable number of hidden neurons has been selected based on comparative analysis for getting lower MSE and higher [Formula: see text] in the validation set. Then, the fitting network with selected training algorithm has been run on the same extracted datasets until the stopping condition is reached. Then the test set images are fed into the network and the network output has been categorized to class which has been assigned to each breed of pig in Breed Prediction Module. The proposed framework has been able to predict breeds with 96.00% accuracy, achieved by the trial with 50 images of the test set. It may be concluded that the Neuro Statistic Neural Network model may be used for breed prediction of pigs by using images of individual pigs.

show abstract

“…The challenge is then to combine single user QoE optimization with a QoE training mechanism in a closed-loop manner to progressively learn the value of W * . To do so, we develop two sub-frameworks and make them interact together within a closed-loop based framework, one is for QoE optimization and the other is for QoE training (see Fig.4 and Fig.5); 2) QoE training tool: To compute W * , we use a simple neural network [17], where the training samples are couples of QoE metrics and user feedback. We define the training dataset as {(Φ * ru , F ru )} 1≤u≤U , where Φ * ru is the vector of QoE metrics delivered by (10) under throughput r u and vector W. F ru being the corresponding feedback.…”

Section: B Practical Solutionmentioning

confidence: 99%

Learning from experience: A dynamic closed-loop QoE optimization for video adaptation and delivery

Triki

El-Azouzi

Haddad

et al. 2017

2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC)

View full text Add to dashboard Cite

The quality of experience (QoE) is known to be subjective and context-dependent. Identifying and calculating the factors that affect QoE is indeed a difficult task. Recently, a lot of effort has been devoted to estimate the users' QoE in order to improve video delivery. In the literature, most of the QoE-driven optimization schemes that realize trade-offs among different quality metrics have been addressed under the assumption of homogenous populations. Nevertheless, people perceptions on a given video quality may not be the same, which makes the QoE optimization harder. This paper aims at taking a step further in order to address this limitation and meet users' profiles. To do so, we propose a closed-loop control framework based on the users' (subjective) feedbacks to learn the QoE function and optimize it at the same time. Our simulation results show that our system converges to a steady state, where the resulting QoE function noticeably improves the users' feedbacks.Index Terms-QoE, learning, neural network, average video quality, startup delay, video quality switching, video stalls, rebuffering delay.

show abstract

Adaptive Algorithms for Neural Network Supervised Learning: A Deterministic Optimization Approach

Cited by 20 publications

References 78 publications

Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review

Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review

A Framework for Selection of Training Algorithm of Neuro-Statistic Model for Prediction of Pig Breeds in India

Learning from experience: A dynamic closed-loop QoE optimization for video adaptation and delivery

Contact Info

Product

Resources

About