i used #wolframalpha to find weights and biases for #neuralnetwork to produce given output for some inputs.

my conditions were:

- for input 99, output should be 2

- for input 50, output should be 100

here is the query i gave to wolfram:

max(0, (a * max(0, (b * 99) + c) + d * max(0, (0.4 * 99) + 0.2)) + 0.3) == 2 and max(0, (a * max(0, (b * 50) + c) + d * max(0, (0.4 * 50) + 0.2)) + 0.3) == 100

task for wolfram was to find correct values for weights a, b and biases c, d

wolfram alpha was able to solve this equation and find suitable values:

a = 1

b = -2007/(995*a)+1

c = (5*a*b + 2007)/(10*a)

d = -5/2*(a*b + 2)

https://www.wolframalpha.com/input?i=max(0%2C+(a+*+max(0%2C+(b+*+99)+%2B+c)+%2B+d+*+max(0%2C+(0.4+*+99)+%2B+0.2))+%2B+0.3)+%3D%3D+2+and+max(0%2C+(a+*+max(0%2C+(b+*+50)+%2B+c)+%2B+d+*+max(0%2C+(0.4+*+50)+%2B+0.2))+%2B+0.3)+%3D%3D+100

Reply to this note

Please Login to reply.

Discussion

No replies yet.