Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking (...) machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models. (shrink)

This essay challenges the widely accepted principle that a person is morally responsible for what he has done only if he could have done otherwise. The author considers situations in which there are sufficient conditions for a certain choice or action to be performed by someone, So that it is impossible for the person to choose or to do otherwise, But in which these conditions do not in any way bring it about that the person chooses or acts as he (...) does. In such situations the person may well be morally responsible for what he chooses or does despite his inability to choose or to do otherwise. Finally the author considers certain suggestions for revising the principle he rejects or for replacing it with a principle of an altogether different kind. (shrink)

I propose a theory of freedom of choice on which it is a variable quality of individual conscious choices that has several dimensions that admit of degrees, even though - as many theorists have traditionally supposed - it also has as a necessary condition the possession of a capacity that is all or nothing. I argue that the proposed account better fits the phenomenology of ostensibly free actions, as well as empirical findings in the human sciences.

Bell’s theorem admits several interpretations or ‘solutions’, the standard interpretation being ‘indeterminism’, a next one ‘nonlocality’. In this article two further solutions are investigated, termed here ‘superdeterminism’ and ‘supercorrelation’. The former is especially interesting for philosophical reasons, if only because it is always rejected on the basis of extra-physical arguments. The latter, supercorrelation, will be studied here by investigating model systems that can mimic it, namely spin lattices. It is shown that in these systems the Bell inequality can be violated, (...) even if they are local according to usual definitions. Violation of the Bell inequality is retraced to violation of ‘measurement independence’. These results emphasize the importance of studying the premises of the Bell inequality in realistic systems. (shrink)