Functional extreme learning machine

Published on July 11, 2023

Imagine you’re trying to build a high-performance race car, but you want to streamline the process and get faster results. That’s where the Functional Extreme Learning Machine (FELM) comes in. Just like a skilled mechanic who knows all the ins and outs of building a powerful engine, the FELM uses functional neurons as its basic units, guided by the principles of functional equation solving theory. By adjusting the coefficients of the basis functions in these neurons, the FELM learns and adapts, making it a lightning-fast and precise learning algorithm. In fact, it outperforms traditional methods like the ELM and support vector machine (SVM) in achieving better performance on regression problems. With its simple yet powerful approach, the FELM shows great promise for revolutionizing the field of machine learning.

To dive deeper into the details of this groundbreaking research, check out the full article linked above!

IntroductionExtreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. However, the ELM also has some shortcomings, such as structure selection, overfitting and low generalization performance.MethodsThis article a new functional neuron (FN) model is proposed, we takes functional neurons as the basic unit, and uses functional equation solving theory to guide the modeling process of FELM, a new functional extreme learning machine (FELM) model theory is proposed.ResultsThe FELM implements learning by adjusting the coefficients of the basis function in neurons. At the same time, a simple, iterative-free and high-precision fast parameter learning algorithm is proposed.DiscussionThe standard data sets UCI and StatLib are selected for regression problems, and compared with the ELM, support vector machine (SVM) and other algorithms, the experimental results show that the FELM achieves better performance.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>