Explore Courses Blog Tutorials Interview Questions
0 votes
in AI and Deep Learning by (50.2k points)

Let's say you have 3 inputs: A, B, C. Can an Artificial Neural Network (not necessarily feed-forward) learn this pattern?

if C > k

   output is A


   output is B

Are there certain types of networks, which can or are well suited for this type of problem?

1 Answer

0 votes
by (108k points)

The key challenge to our joint learning problem lies in recovering the optimal multiplexing pattern I(n) since it is ordinal-valued and requires learning to make a hard non-differentiable decision between C possibilities. To address this, we rely on the standard soft-max operation, which is traditionally used in multi-label classification tasks. If you know the structure of your problem and what kind of calculation you want to perform, then Neural Network are unlikely to be the most effective solution: they are better in situations when you don't know much about the exact calculations required to model the functions/relationships. For more information regarding the same, refer to the following link:

Browse Categories