Supervised Training Using Global Search Methods

Plagianakos, Vassilis P.; Magoulas, George D.; Vrahatis, Michael N.

doi:10.1007/978-1-4613-0279-7_26

Cited by 8 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although intuitively it makes sense that accurate initial mappings would set learners on a fast track to vocabulary knowledge, this might not necessarily be the case. Indeed, studies in neural network learning suggest that under certain circumstances initial correct guesses can leave the system stranded in local minima from which it cannot easily escape (Gori & Tesi, ; Plagianakos, Magoulas, & Vrahatis, ). In addition, although correct initial biases in combination with supporting subsequent evidence could be sufficient for learning (e.g., Xu & Tenenbaum, ), learning may be more efficient with errors because errors clearly rule out alternatives.…”

Section: Introductionmentioning

confidence: 99%

Developmental Changes in Cross‐Situational Word Learning: The Inverse Effect of Initial Accuracy

Fitneva

Christiansen

2015

Cognitive Science

View full text Add to dashboard Cite

Intuitively, the accuracy of initial word-referent mappings should be positively correlated with the outcome of learning. Yet recent evidence suggests an inverse effect of initial accuracy in adults, whereby greater accuracy of initial mappings is associated with poorer outcomes in a cross-situational learning task. Here, we examine the impact of initial accuracy on 4-year-olds, 10-year-olds, and adults. For half of the participants most word-referent mappings were initially correct and for the other half most mappings were initially incorrect. Initial accuracy was positively related to learning outcomes in 4-year-olds, had no effect on 10-year-olds' learning, and was inversely related to learning outcomes in adults. Examination of item learning patterns revealed item interdependence for adults and 4-year-olds but not 10-year-olds. These findings point to a qualitative change in language learning processes over development.

show abstract

Section: Introductionmentioning

confidence: 99%

Developmental Changes in Cross‐Situational Word Learning: The Inverse Effect of Initial Accuracy

Fitneva

Christiansen

2015

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…One of the major drawbacks of BP algorithm is convergence to local minima [40]. However, the reality of local minima is a consequence of the fact that the error curvature is simply the superposition of non-linear activation functions that may exhibit local minima at different locations, which occasionally results in a non-convex curvature of the error cost function [41], [42]. One way to overcome this challenge is through the use of improved gradient-based algorithms that employ parameter adaptation strategies [43].…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Optimal design for real-time quantitative monitoring of sand in gas flowline using computational intelligence assisted design framework

Aminu

McGlinchey

Chen

2019

Journal of Petroleum Science and Engineering

View full text Add to dashboard Cite

Global demand for oil and gas is still increasing rapidly. The direct consequence of this is the increased operating pressure amid concerns over increasing sand production. According to the Society of Petroleum Engineers (SPE), 70% of the world's hydrocarbon reserves are contained in reservoirs situated on unconsolidated formations. Given the reality of these formations, sand production will certainly be a problem of significant concern particularly during the later life of the fields when they become more 'mature'. However, to monitor sand and optimise its production for improved recovery and safety, life extension and economy of the fields and ensured reliability, the automatic detection and prediction of sand flow characteristic measurements; sand flow rate (SFR), sand concentration (SC), line pressure drop (PD), and gas velocity (GV), has become an important research topic of great interest. Despite this importance, discussion of the topic is still lacking in the literature. This paper proposes a novel and robust architecture of intelligent real-time sand flow characteristic measurement using an acoustic sensor and computational intelligence assisted design (CIAD) framework. It fully incorporates acoustic signal processing and analysis, prediction algorithms and optimisation algorithms in the design. Acoustic features based on acoustic signal processing techniques are extracted to reduce the dimensionality of the acoustic signals. A classical Artificial Neural Network (ANN) is used to model the non-linear relationships between the acoustic signal characteristics and the flow characteristics measurands. In addition, the ANN algorithm adapts its weights and biases using the Grey Wolf Optimiser (GWO) through minimisation of the cost function during the training phase. Preliminary results obtained on a laboratory test rig demonstrate that an acoustic sensor coupled with CIAD may provide simple and robust practical solution to the measurement problem of particle-laden gas flow characteristics in real-time.

show abstract

“…Herein, this algorithm includes local minimization methods that have no mechanism allowing them to escape from the influence of a local minimum [12]. At this point, optimization algorithms are added to NN for prevention of this problem.…”

Section: Introductionmentioning

confidence: 99%

RF Ensemble Novelties Based on Optimized & Backpropagated NNs

Koyuncu¹,

Ceylan²

2017

IJMLC

View full text Add to dashboard Cite

Abstract-This paper presents a classifier model based on Rotation Forest (RF) ensemble structure for biomedical data classification. Classifiers based on RF are generally implemented by using Decision Trees. In this study, optimized Neural Network (NN) is preferred as being the base classifier in RF so as to achieve higher classification performance. Two optimization techniques, Artificial Bee Colony Optimization (ABC) and Particle Swarm Optimization (PSO), are utilized to improve the performance of NN for escaping from local minima. In this way, PSO-NN and ABC-NN based RF structures are designed, and they are called as RF (PSO-NN) and RF (ABC-NN), respectively. In these classifiers, initial weights of NNs are found by using PSO or ABC algorithms. The implemented classifiers based on RF are applied to biomedical datasets (Wisconsin Breast Cancer and Pima Indian Diabetes) that are taken from UCI Machine Learning Repository. Furthermore, fourteen different ensemble structures are generated using these algorithms to prove the superiority of the proposed method. When the results are examined using several performance metrics, it is seen that RF (ABC-NN) classifier achieves to more reliable and better results than other classifiers.Index Terms-Rotation forest, particle swarm optimization, artificial bee colony optimization, neural networks, biomedical data classification.

show abstract

Supervised Training Using Global Search Methods

Cited by 8 publications

References 20 publications

Developmental Changes in Cross‐Situational Word Learning: The Inverse Effect of Initial Accuracy

Developmental Changes in Cross‐Situational Word Learning: The Inverse Effect of Initial Accuracy

Optimal design for real-time quantitative monitoring of sand in gas flowline using computational intelligence assisted design framework

RF Ensemble Novelties Based on Optimized & Backpropagated NNs

Contact Info

Product

Resources

About