Sort by
Refine Your Search
-
. The BayesCompare project is a FNR funded project on Bayesian comparisons between artificial and natural representations to improve our understanding how natural and artificial intelligences process information
-
behaviour using computational approaches such as Bayesian program synthesis and inverse reinforcement learning. Investigate the diversity of motor commands that could implement observed behaviours and explore
-
Inria, the French national research institute for the digital sciences | Villeneuve la Garenne, le de France | France | 3 months ago
of competing agents when an agent makes a decision. A first approach, inspired by the Bayesian games literature, consists in considering a stochastic formulation where the competitors’ strategies are represented
-
using copulas [4] as in e.g. [2]. A longer-term objective is to study the extension of the approach to the analysis of Bayesian neural networks, where the weights and bias of the network are also defined