Is each architecture given one set of random weights?
Or is the architecture of the net tested against a bunch of random weights so that it performs well independently of the weights?
Or is the architecture of the net tested against a bunch of random weights so that it performs well independently of the weights?
From the paper :
(1) An initial population of minimal neural network topologies is created
(2) each network is evaluated over multiple rollouts, with a different shared weight value assigned at each rollout
(3) networks are ranked according to their performance and complexity
(4) a new population is created by varying the highest ranked network topologies, chosen probabilistically through tournament selection
Shared weight here means that every neuron in the network shares the exact same weight value.