At the moment, it seems that the implementation of the NEAT network only allows a fixed size input to be computed, and the network is reset afterwards. NEAT networks can function as recurrence networks, so it would be nice if I could feed a stream of inputs into the NEAT network and utilise the internal state that can be established by recurrent neurons.
Hello,
At the moment, it seems that the implementation of the NEAT network only allows a fixed size input to be computed, and the network is reset afterwards. NEAT networks can function as recurrence networks, so it would be nice if I could feed a stream of inputs into the NEAT network and utilise the internal state that can be established by recurrent neurons.
Thank you