A Fast Learning Algorithm Based on Layered Hessian Approximations and the Pseudoinverse

2006 ◽  
pp. 530-536
Author(s):  
E. J. Teoh ◽  
C. Xiang ◽  
K. C. Tan
Keyword(s):  
Learning Algorithm ◽  
Fast Learning

scholarly journals A Robust AdaBoost.RT Based Ensemble Extreme Learning Machine

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Pengbo Zhang ◽  
Zhixin Yang
Keyword(s):  
Extreme Learning Machine ◽  
Learning Algorithm ◽  
Approximation Accuracy ◽  
Weak Learner ◽  
Fast Learning ◽  
Learning Speed ◽  
Regression Problems ◽  
Learning Machine ◽  
The Stability ◽  
Stability And Accuracy

Extreme learning machine (ELM) has been well recognized as an effective learning algorithm with extremely fast learning speed and high generalization performance. However, to deal with the regression applications involving big data, the stability and accuracy of ELM shall be further enhanced. In this paper, a new hybrid machine learning method called robust AdaBoost.RT based ensemble ELM (RAE-ELM) for regression problems is proposed, which combined ELM with the novel robust AdaBoost.RT algorithm to achieve better approximation accuracy than using only single ELM network. The robust threshold for each weak learner will be adaptive according to the weak learner’s performance on the corresponding problem dataset. Therefore, RAE-ELM could output the final hypotheses in optimally weighted ensemble of weak learners. On the other hand, ELM is a quick learner with high regression performance, which makes it a good candidate of “weak” learners. We prove that the empirical error of the RAE-ELM is within a significantly superior bound. The experimental verification has shown that the proposed RAE-ELM outperforms other state-of-the-art algorithms on many real-world regression problems.

A fast learning algorithm for time-delay neural networks

2002 ◽  
Vol 148 (1-4) ◽  
pp. 27-39 ◽  
Author(s):  
Minghu Jiang ◽  
Georges Gielen ◽  
Beixing Deng ◽  
Xiaoyan Zhu
Keyword(s):  
Neural Networks ◽  
Time Delay ◽  
Learning Algorithm ◽  
Fast Learning

A Fast Learning Algorithm for Deep Belief Nets

2006 ◽  
Vol 18 (7) ◽  
pp. 1527-1554 ◽  
Author(s):  
Geoffrey E. Hinton ◽  
Simon Osindero ◽  
Yee-Whye Teh
Keyword(s):  
Greedy Algorithm ◽  
Associative Memory ◽  
Learning Algorithm ◽  
Generative Model ◽  
Fine Tuning ◽  
Discriminative Learning ◽  
Fast Learning ◽  
Learning Procedure ◽  
Handwritten Digit ◽  
Low Dimensional

We show how to use “complementary priors” to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modeled by long ravines in the free-energy landscape of the top-level associative memory, and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind.

FUSION OF EXTREME LEARNING MACHINE WITH FUZZY INTEGRAL

2013 ◽  
Vol 21 (supp02) ◽  
pp. 23-34 ◽  
Author(s):  
JUNHAI ZHAI ◽  
HONGYU XU ◽  
YAN LI
Keyword(s):  
Extreme Learning Machine ◽  
Learning Algorithm ◽  
Fuzzy Integral ◽  
Fast Learning ◽  
Original Dataset ◽  
Learning Speed ◽  
Feed Forward Neural Networks ◽  
Three Stages ◽  
Learning Machine ◽  
Hidden Layer

Extreme learning machine (ELM) is an efficient and practical learning algorithm used for training single hidden layer feed-forward neural networks (SLFNs). ELM can provide good generalization performance at extremely fast learning speed. However, ELM suffers from instability and over-fitting, especially on relatively large datasets. Based on probabilistic SLFNs, an approach of fusion of extreme learning machine (F-ELM) with fuzzy integral is proposed in this paper. The proposed algorithm consists of three stages. Firstly, the bootstrap technique is employed to generate several subsets of original dataset. Secondly, probabilistic SLFNs are trained with ELM algorithm on each subset. Finally, the trained probabilistic SLFNs are fused with fuzzy integral. The experimental results show that the proposed approach can alleviate to some extent the problems mentioned above, and can increase the prediction accuracy.

scholarly journals The Extended Multidimensional Neo-Fuzzy System and Its Fast Learning in Pattern Recognition Tasks

Data ◽  
2018 ◽  
Vol 3 (4) ◽  
pp. 63 ◽  
Author(s):  
Yevgeniy Bodyanskiy ◽  
Nonna Kulishova ◽  
Olha Chala
Keyword(s):  
Real Time ◽  
Information Technologies ◽  
Learning Algorithm ◽  
Video Stream ◽  
System Structure ◽  
System Architectures ◽  
Fast Learning ◽  
Video Recognition ◽  
Entropy Criterion ◽  
Time Image

Methods of machine learning and data mining are becoming the cornerstone in information technologies with real-time image and video recognition methods getting more and more attention. While computational system architectures are getting larger and more complex, their learning methods call for changes, as training datasets often reach tens and hundreds of thousands of samples, therefore increasing the learning time of such systems. It is possible to reduce computational costs by tuning the system structure to allow fast, high accuracy learning algorithms to be applied. This paper proposes a system based on extended multidimensional neo-fuzzy units and its learning algorithm designed for data streams processing tasks. The proposed learning algorithm, based on the information entropy criterion, has significantly improved the system approximating capabilities. Experiments have confirmed the efficiency of the proposed system in solving real-time video stream recognition tasks.

Sign in / Sign up

Export Citation Format

Share Document