A controller-peripheral architecture and costly energy principle for learning
Xiaoliang Luo, Robert M. Mok, Brett D. Roads, Bradley C. Love
The paper proposes a controller-peripheral architecture to model brain coordination for learning, showing how higher-level control shapes lower-level representations and outperforms gradient descent models.
Conference on Cognitive Computational Neuroscience (CCN) · Jan 1, 2023Peer-reviewedNeuroscience