Neural network weights and topologies were originally evolved in order to solve tasks where gradients are not available. Recently, it has also become a useful technique for metalearning architectures of deep learning networks. However, neuroevolution is most powerful when it utilizies synergies of evolution and learning. In this talk I review four examples of such synergies: evolving loss functions, co-adapting learning and evolution, evolving activation functions, and evolving decision-making based on surrogate learning. I will demonstrate these synergies in image recognition, game playing, and pandemic policy optimization, and point out opportunities for future work.

, 2021. Plenary presentation at the Congress for Evolutionary Computation (CEC'21).

@misc{miikkulainen:cec21plenary, title={Neuroevolution: A Synergy of Evolution and Learning }, author={Risto Miikkulainen}, month={ }, note={Plenary presentation at the Congress for Evolutionary Computation (CEC'21)}, url="http://nn.cs.utexas.edu/?miikkulainen:cec21plenary", year={2021} }

Video