Research Theme: Artificial Intelligence

A Machine Theory of Mind
Epistemic Artificial Intelligence

We support the view that a fruitful cross-fertilisation of neuroscience and artificial intelligence can enable significant advances in both fields, by allowing: (i) the formulation of computational theory of mind models in humans leveraging current frontier efforts in AI; (ii) the development of machine theory of mind models informed by the most recent neuroscientific evidence, capable of going beyond simple pattern recognition for prediction in complex, human-centred scenarios.

As currently practised, AI cannot confidently make predictions robust enough to stand the test of data generated by processes different (even by tiny details, as shown by "adversarial" results able to fool deep neural networks) from those studied at training time. While recognising this issue under different names (e.g. "overfitting"), traditional machine learning seems unable to address it in nonincremental ways.
Epistemic AI's overall objective is to create a new paradigm for a next-generation artificial intelligence providing worst-case guarantees on its predictions thanks to a proper modelling of real-world uncertainties.