ES-HyperNEAT algorithm
The ES-HyperNEAT algorithm starts with user-defined input nodes and elaborates on exploring connections from them and sending them to the newly expressed hidden nodes. The expression of outgoing connectivity patterns and hidden nodes placement within the substrate space is done using the quadtree information extraction method, which we described previously. The information extraction process is iteratively applied until the desired level of information expression density is achieved, or until no more information can be discovered in the hypercube. After that, the resulting network is connected to the user-defined output nodes by expressing the incoming connectivity patterns to the outputs. We use quadtree information ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access