2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Neuroevolution is established as a competitive alternative to RL under continual task changes, and it is suggested that training under perturbations in weight space may be a useful mechanism for continual learning more broadly.
The results provide a computational realization of D'Arcy Thompson's remarkable grid transformations in a 2D NCA---a minimal cybernetic tissue in which variations of fully grown emoji phenotypes can be encoded, combined, and controlled through low-dimensional directions in regulatory weight space.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
