Bayes in the age of intelligent machines
This addresses the theoretical challenge of integrating Bayesian models with neural networks for cognitive science and AI, but it is incremental as it builds on existing debates.
The paper argues that Bayesian inference and artificial neural networks are complementary modeling approaches for understanding human cognition and intelligent machines, offering new opportunities for Bayesian modeling despite the success of neural networks.
The success of methods based on artificial neural networks in creating intelligent machines seems like it might pose a challenge to explanations of human cognition in terms of Bayesian inference. We argue that this is not the case, and that in fact these systems offer new opportunities for Bayesian modeling. Specifically, we argue that Bayesian models of cognition and artificial neural networks lie at different levels of analysis and are complementary modeling approaches, together offering a way to understand human cognition that spans these levels. We also argue that the same perspective can be applied to intelligent machines, where a Bayesian approach may be uniquely valuable in understanding the behavior of large, opaque artificial neural networks that are trained on proprietary data.