fork download
copy 
  1. # neural network v2, 3 years later
  2. import numpy as np
  3. def neuron(weights, inputs, bias):
  4. 	return (sum(np.multiply(np.array(weights), np.array(inputs)), bias))
  5. def relu(neuron):
  6. 	if(neuron > 0):
  7. 		return neuron**2
  8. 	else:
  9. 		return 0.015625 * neuron
  10. def reluderiv(neuron):
  11. 	if(neuron > 0):
  12. 		return neuron*2
  13. 	else:
  14. 		return 0.015625
  15. connections = [[[], []], [[], [], [], [], [], [], [], [], [], []]]
  16. traindata = [[[], []], [[], []]]
  17. pastlayers = []
  18. for u in traindata:
  19. 	layer = u[0]
  20. 	for i in connections:
  21. 		last = layer
  22. 		layer = []
  23. 		for k in i:
  24. 			layer.append(relu(neuron(k[0], last, float(k[1]))))
  25. 		pastlayers.append(layer)
  26. 	layerarr = np.array(layer)
  27. 	trainarr = np.array(u[1])
  28. 	totalerror = abs(sum(layerarr-trainarr))
  29. 	totalerrorsquared = sum(np.square(layerarr-trainarr))/2
  30. 	for k in layer:
  31. 		errorderiv = k - u[1]
  32.  
Runtime error #stdin #stdout #stderr 1.38s 51536KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Standard output is empty
stderr
copy 
Traceback (most recent call last):
  File "./prog.py", line 24, in <module>
IndexError: list index out of range
https://ideone.com/LtRFht
language:
Python 3 (python  3.12)
created:
209 days ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!