Jonathan Brant
Sep 5, 2018 · 1 min read

To tack on to the below statement, one interesting idea is to treat nodes as layers and optimize the number of nodes in any given layer rather than stochastically adding/removing individual nodes. That seems to be similar to what was done in Miikkulainen 2017 (Evolving Deep Neural Networks) and Assuncao 2018 (DENSER).

    Jonathan Brant

    Written by

    Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
    Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
    Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade