This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
Today I want to try some basic examples for the Neural Network predictive tool. Here is a simple workflow for testing.
I don't understand why this Neural Network cannot learn this simple XOR table. I can see that the output scores are the same whether I use integer or string inputs. Here are the scores I get for both inputs separately:
0.491321 0.491856 0.491858 0.492392
A solution should exist with only 1 hidden layer of 2 nodes. Maybe I am doing something wrong?