Lab - Regression with a MLP
Lab - Regression with a MLP
Description
The goal is to estimate the position X of a bullet at time t (fixed) given the initial speed (v) and angle (a):
Files
souce code (canonball.cc)
How play with the code ?
1. Go to lines 34 and 35 to change the number of patterns to generate:
2. Go to lines 64, 65, 66 and 67 to change the training parameters:
3. Go to lines 72 to change the number of hidden neurons:
4.Re-compile
5. Run it and plot the files "mse_train.txt" and "mse_test.txt"
Ackowledgment
I would like here to address a special thank to Daniel Collobert. Thanks to him, I discovered Artificial Neural Networks and he provided me with introductory examples such as this one.