问题
Please, let me know if this question should be posted in a differnt stack such as the https://datascience.stackexchange.com/.
Let's say that I already trained my CNN. Is there anyway of my ouput to be represented as a formula just like a perceptron can (x1w1 + x2w2 + ... = PREDICTION).
It does not matter if the formula is more complicated than the perceptron one, but in general would it be possible to train a CNN in Python or Matlab, get the weights and create an arithmetic, exponential, whatever formula made with those acquired weights?
I want to do this because I am trying classify in a PIC32 (a low cost microchip) which I think that does not have the capacity to perform a CNN within itself.
Or, for example, should I pursue the idea of some sort of "C library" that can do CNNs?
回答1:
If you can sacrifice some memory, you can certainly convert a convolution into a matrix multiplication.
It turns out to have its own pros (faster than any trivial implementation unless you optimize really seriously) and cons (large memory consumption).
来源：https://stackoverflow.com/questions/55270799/can-convolutional-neural-networks-cnn-be-represented-by-a-mathematical-formula