Hi all,

We'll have a special guest next Thursday, Peter Railton, a philosopher teaching at U. Michichigan, Ann Arbor. He will talk on Morality and AI, note that it's not in the usual tea-talk slot but during the department colloquium (3pm for the munchies, 3:30pm for the talk). I heard him talk last Fall and I was quite impressed (about how well he understand current deep-learning based AI from a philosophical standpoint).

If you are interested in chatting with him during his visit, please contact Michael (in cc) and he will set up a meeting schedule.

-- Yoshua

---------- Forwarded message ---------- From: Gilles Brassard brassard@iro.umontreal.ca Date: 2018-01-11 5:28 GMT-05:00 Subject: Prochain Colloque du DIRO jeudi prochain, 18 janvier To: seminaires@iro.umontreal.ca Cc: Yoshua Bengio yoshua.umontreal@gmail.com

Bonjour tout le monde

Le premier Colloque du DIRO de la session (et donc de l'année 2018) aura lieu jeudi prochain. Ne ratez pas cette chance ! :-)

Conférencier : Peter Railton

Affiliation : University of Michigan, Ann Arbor

Endroit : Z330 Pavillon Claire-McNicoll Université de Montréal

Quand : le 18 janvier 2018, 15h30 (café et biscuits à partir de 15h)

Titre : Moral Learning and Artificial Intelligence (la conférence sera présentée en anglais)

Résumé : Traditional approaches to moral development have emphasized the explicit teaching of norms, e.g., via parental instruction, or the acquisition of behavioral dispositions by “social learning”, e.g., via infant imitation and modeling of observed behaviors, or progression through a fixed set of developmental “stages”. But what if we understood moral learning as closer to causal learning and the development of commonsense physics? Developmental evidence suggests that infants early on begin to model their physical environment and its possibilities (Gopnik & Schulz, 2004), using observation but receiving very limited explicit instruction or external reinforcement. Similarly, there is evidence that infants early on begin learning a kind of commonsense psychology that enables them to model others’ behavior in terms of intentional states, once again, using observation but very limited explicit instruction or external reinforcement (Wellman, 2014). These internal models enable infants to interact reasonably successfully with their physical and social environment even if they are unable to articulate the causal or psychological principles involved—the knowledge underlying these capacities is therefore generalizable despite being implicit, and so is spoken of as intuitive. Internal models are not limited to causal and predictive information, however, but also appear to encode evaluative information, including evaluation of possible actions or third-party social interactions for such features as helpfulness, harm, knowledgeability, and trustworthiness (Hamlin et al., 2011; Doebel & Koenig, 2013). When combined with an implicit capacity to empathically simulate the mental states of others, these evaluative capacities can underwrite a kind of intuitive learning of commonsense morality. Such learning occurs without much explicit instruction in moral principles, yet with a capacity to generalize and with some degree of moral autonomy—so that by age 3-4, infants will resist conforming to imposed rules that involve harm or unfairness toward others (Turiel, 2002).

To be genuinely intelligent, artificial systems will need to possess the kinds of intuitive knowledge involved in commonsense physics and psychology. And to be both autonomous and trustworthy, artificial systems will need to be able to evaluate situations, actions, and agents in the terms of such categories of commonsense morality as helpfulness, harm, knowledgeability, and trustworthiness. Deep learning approaches suggest how intuitive knowledge of the kind involved in predictive learning might be acquired and represented, without being “programmed in” or explicitly taught. How might further developments of these approaches make possible the acquisition of intuitive evaluative knowledge of the kind involved in commonsense epistemic or moral assessment?

Biographie : Peter Railton is the G.S. Kavka Distinguished University Professor in the Department of Philosophy at the University of Michigan, Ann Arbor. His main research has been in ethics and the philosophy of science, focusing especially on questions about the nature of objectivity, value, norms, and explanation. Recently, he has also begun working in aesthetics, moral psychology, and the theory of action, and on the bearing of empirical research in these areas. Among his publications are Facts, Values, and Norms (Cambridge), a collection of some of his papers in ethics and meta-ethics, and Homo Prospectus (Oxford), a joint project with psychology and neuroscience on basic mental architecture. He has been a visiting professor at Berkeley and Princeton, and he has received fellowships from the ACLS, the NEH, and the Guggenheim Foundation. He is a former President of the American Philosophical Association (Central Division) and is a Fellow of the American Academy of Arts and Sciences.

Venez nombreux !

- Gilles et Yoshua, responsables du Colloque