© Igor Livshin 2019
Igor LivshinArtificial Neural Networks with Javahttps://doi.org/10.1007/978-1-4842-4421-0_9

9. Approximating Continuous Functions with Complex Topology

Igor Livshin1 
(1)
Chicago, IL, USA
 

This chapter shows that the micro-batch method substantially improves the approximation results of continuous functions with complex topologies.

Example 5a: Approximation of a Continuous Function with Complex Topology Using the Conventional Network Process

Figure 9-1 shows one such function. The function has the following formula: y $$ =\sqrt{e^{-\left(\sin \left({e}^x\right)\right)}} $$ . However, let’s pretend that the function formula is unknown and that the function is given to you by its values at ...

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

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.