Closed seanshpark closed 7 years ago
In a Layer, there are N neurons. For a neuron n, where 0 <= n < N, having P input with W[p] weights where 0 <= p < P
N
n
0 <= n < N
P
W[p]
0 <= p < P
sumweights = sum(W[p] * input[p]) output[n] = 1.0 / (1.0 + exp(-1.0 * gain * sumweights))
https://en.wikipedia.org/wiki/Artificial_neuron#Basic_structure
input weight 0 -- w[0] --+-- sigmoid -- 1 -- w[1] --+ . p -- w[p] --+ . P-1 -- w[P-1] --+
sigmoid function: https://en.wikipedia.org/wiki/Sigmoid_function
sum(w[p] * input[p]), where 0 <= p < P
How to run this with OpenGLSL?
To read: http://www.lighthouse3d.com/tutorials/glsl-12-tutorial/shader-examples/
Use QPULib.
In a Layer, there are
N
neurons. For a neuronn
, where0 <= n < N
, havingP
input withW[p]
weights where0 <= p < P
https://en.wikipedia.org/wiki/Artificial_neuron#Basic_structure
sigmoid function: https://en.wikipedia.org/wiki/Sigmoid_function