Bayesian Integration of Information Using Top-Down Modulated WTA Networks

1 code implementation • 29 Aug 2023 • Otto van der Himst, Leila Bagheriye, Johan Kwisthout

The results show that WTA circuits are capable of integrating the probabilistic information represented by other WTA networks, and that top down processes can improve a WTA network's inference and learning performance.

Deep Active Inference for Partially Observable MDPs

1 code implementation • 8 Sep 2020 • Otto van der Himst, Pablo Lanillos

Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces.

Q-Learning reinforcement-learning +1