Demonstrate the use of CMA-ES for training transformers
Explore and demonstrate the use of evolutionary methods (EMs) such as Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for training various Deep Neural Networks (DNNs) including transformer networks. Such exploration could include using EMs to determine model node weights, using EMs to evolve DNN/LLM architectures, or even using EMs for conceiving and designing completely new “evolutionary DNNs” (e.g. integrating LLM and evolutionary methods in new DNN architectures, with LLM for direction and evolution for invention)