© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2022
I. LivshinArtificial Neural Networks with Javahttps://doi.org/10.1007/978-1-4842-7368-5_8

8. Approximating Noncontinuous Functions

Igor Livshin1  
(1)
Chicago, IL, USA
 

In this chapter, we will discuss the neural network approximation of noncontinuous functions. Currently, this is a problematic area for neural networks because network processing is based on the calculation of partial function derivatives (gradient descent algorithm), and our ability to calculate them for noncontinuous functions at the points where the function value suddenly jumps or drops is questionable. We will dig into this issue later in this chapter. The chapter includes method that I ...

Get Artificial Neural Networks with Java: Tools for Building Neural Network Applications now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.