Towards a Human-Like Observer: Applying Deep Learning in an Extended Wigner’s Friend Experiment

Abstract There has been a longstanding demand for artificial intelligence with human-level cognitive sophistication to address loopholes in Bell-type experiments. In this study, we introduce a novel experimental framework that incorporates advanced deep learning techniques, utilizing neural network-based artificial intelligence within an extended Wigner’s Friend experiment as a crucial step toward developing a human-like observer. We demonstrate the framework through simulations and introduce three new analytical metrics—morphing polygons, averaged Shannon entropy, and probability density maps—to evaluate the results. These results can be used to determine whether our artificial intelligence qualifies as a bona fide observer and whether superposition applies to macroscopic systems, including observers.