January 2020
Intermediate to advanced
346 pages
9h 8m
English
The genetic algorithm-based search for the best combination of hidden layers and hyperparameters is implemented by the Python program 02-optimize-mlp-hyperparameters.py, which is located at https://github.com/PacktPublishing/Hands-On-Genetic-Algorithms-with-Python/blob/master/Chapter09/02-optimize-mlp-hyperparameters.py.
Thanks to the unified floating number representation that's used for all parameters, this program is almost identical to the one we used in the previous section to optimize the network architecture. The main difference is in the definition of the BOUNDS_LOW and BOUNDS_HIGH lists, which contain the ranges of the parameters. Regarding the four ranges we defined ...
Read now
Unlock full access