Python Module Index

a | c | g | i | m | n | p | r | s
 
a
activations Has the built-in activation functions and code for using them and adding new user-defined ones.
attributes Deals with attributes used by genes.
 
c
checkpoint Uses `pickle` to save and restore populations (and other aspects of the simulation state).
config Does general configuration parsing; used by other classes for their configuration.
ctrnn Handles the continuous-time recurrent neural network implementation.
 
g
genes Handles node and connection genes.
genome Handles genomes (individuals in the population).
graphs Directed graph algorithm implementations.
 
i
indexer Contains the Indexer class, to help with creating new identifiers/keys.
iznn Implements a spiking neural network (closer to in vivo neural networks) based on Izhikevich's 2003 model.
 
m
math_util Contains some mathematical functions not found in the Python2 standard library, plus a mechanism for looking up some commonly used functions (such as for the species_fitness_func) by name.
 
n
nn
    nn.feed_forward A straightforward feed-forward neural network NEAT implementation.
    nn.recurrent A recurrent (but otherwise straightforward) neural network NEAT implementation.
 
p
parallel Runs evaluation functions in parallel subprocesses in order to evaluate multiple genomes at once.
population Implements the core evolution algorithm.
 
r
reporting Makes possible reporter classes, which are triggered on particular events and may provide information to the user, may do something else such as checkpointing, or may do both.
reproduction Handles creation of genomes, either from scratch or by sexual or asexual reproduction from parents.
 
s
six_util Provides Python 2/3 portability with three dictionary iterators; copied from the `six` module.
species Divides the population into species based on genomic distances.
stagnation Keeps track of whether species are making progress and helps remove ones that are not (for a configurable number of generations).
statistics Gathers and provides (to callers and/or to a file) information on genome and species fitness, which are the most-fit genomes, and similar.