A review of online learning in supervised neural networks

Jain, Lakhmi C.; Seera, Manjeevan; Lim, Chee Peng; Balasubramaniam, P.

doi:10.1007/s00521-013-1534-4

Cited by 91 publications

(43 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This would have led to training two distinct classifiers and choosing the predicted class as the argmax of their scores, according to Eq. (14). The two approaches are clearly equivalent since the Bayes classifier corresponds respectively to the inequalities ρ(1|x) > ρ(−1|x) or ρ(1|x) > ρ(2|x).…”

Section: E Multiclass Rebalancing and Recodingmentioning

confidence: 99%

Incremental robot learning of new objects with fixed update time

Camoriano

Pasquale

Ciliberto

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification (RLSC) algorithm, and exploit its structure to seamlessly add new classes to the learned model. The presented algorithm addresses the problem of having an unbalanced proportion of training examples per class, which occurs when new objects are presented to the system for the first time.We evaluate our algorithm on both a machine learning benchmark dataset and two challenging object recognition tasks in a robotic setting. Empirical evidence shows that our approach achieves comparable or higher classification performance than its batch counterpart when classes are unbalanced, while being significantly faster.

show abstract

Section: E Multiclass Rebalancing and Recodingmentioning

confidence: 99%

Incremental robot learning of new objects with fixed update time

Camoriano

Pasquale

Ciliberto

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…RBF has good generalization, online learning capability and tolerant to noisy inputs [2]. These advantages make the RBF network widely applied in flexible control systems, dynamic systems and time-series prediction [3][4][5][6][7].…”

Section: Radial Basis Function Networkmentioning

confidence: 99%

A performance evaluation of pruning effects on hybrid neural network

Leow¹,

Yap²,

Yap³

et al. 2018

J. Fundam and Appl Sci.

View full text Add to dashboard Cite

show abstract

“…The artificial neural network, in general, is a system of programs and data design that approximates the process of the human brain [11]. In over the last decade, neural networks have been used to solve the trajectory tracking control problem for a mobile robot.…”

Section: Introductionmentioning

confidence: 99%

Neural Networks Trained with Levenberg-Marquardt-Iterated Extended Kalman Filter for Mobile Robot Trajectory Tracking

Aissa¹,

Chouireb²

2017

JESTR

View full text Add to dashboard Cite

This paper proposes a neural network controller using a new efficient optimisation algorithm for learning that is the Levenberg-Marquart Iterated Extended Kalman filter LM-IEKF. The trained neural network is applied to control a wheeled mobile robot for trajectory tracking problem. The proposed algorithm is compared to the standard extended Kalman filter and the back-propagation algorithms. Simulation and experimental results using MATLAB 7.1 and National Instrumentation mobile robot (starter kit 2.0) respectively show that in terms of mean squared errors, the proposed algorithm is superior to the extended Kalman filter and back-propagation. This indicates that LevenbergMarquart iterated extended Kalman filter based neural networks learning could be a good alternative in the artificial neural networks based applications for mobile robot trajectory tracking.

show abstract

A review of online learning in supervised neural networks

Cited by 91 publications

References 90 publications

Incremental robot learning of new objects with fixed update time

Incremental robot learning of new objects with fixed update time

A performance evaluation of pruning effects on hybrid neural network

Neural Networks Trained with Levenberg-Marquardt-Iterated Extended Kalman Filter for Mobile Robot Trajectory Tracking

Contact Info

Product

Resources

About