The IJCAI distinguished paper awards recognise some of the best papers presented at the conference each year. This year, three articles received the accolade of distinguished paper, with a further article receiving an honourable mention. Learning generalized unsolvability heuristics for classical planning Simon Ståhlberg, Guillem Francès, Jendrik Seipp Recent work in classical planning has introduced dedicated techniques for detecting unsolvable states, that is, states from which no goal state can be reached. The authors approach the problem from a generalized planning perspective and learn first order-like formulas that characterize unsolvability for entire planning domains. On the relation between approximation fixpoint theory and justification theory Simon Marynissen, Bart Bogaerts, Marc Denecker Approximation Fixpoint Theory (AFT) and Justification Theory (JT) are two frameworks to unify logical formalisms.

Welcome to our August 2021 monthly digest where you can catch up with any AIhub stories you may have missed, get the low-down on recent events, and much more. In this edition we cover IJCAI 2021, find out about new grants for climate research, hear about RoboCupJunior, and celebrate a significant birthday. The big event this month was the International Joint Conference on Artificial Intelligence (IJCAI-21), held virtually from 19-26 August. Gathertown played host to proceedings and participants were treated to eight invited talks, panel discussions, poster sessions, and more. We're covering the invited talks in a series of articles.

In this post, we continue our summaries of the invited talks from the International Joint Conference on Artificial Intelligence (IJCAI-21). This time, we cover the presentations from Yoshua Bengio and Michael Thielscher. Yoshua's talk focussed on the development of what he calls system 2 deep learning. The aim is to incorporate agency, causality, and ideas from human intelligence to advance current deep learning methods, thus enabling better out-of-distribution generalisation. As proposed by Daniel Kahneman, system 1 and system 2 are different types of thinking.

There is an exciting, and varied, programme of eight invited talks at the International Joint Conference on Artificial Intelligence (IJCAI-21) this year. On the opening day of the conference, we heard presentations from Edith Elkind (University of Oxford), who talked about fairness in multiwinner voting, and Masahiro Fujita (SonyAI) who discussed combining AI and robotics for augmenting human abilities. Edith works in algorithmic game theory, with a focus on algorithms for collective decision making and coalition formation. She began by giving a brief overview of the field of computational social choice. This area of research, at the interface of social choice theory and computer science, really began in earnest following COMSOC '06, the first International Workshop on Computational Social Choice.

The 30th International Joint Conference on Artificial Intelligence (IJCAI-21), taking place virtually, started on August 19th. The weekend just gone saw the running of numerous workshops and tutorials. We also look ahead to some of the other events planned for this week. The first #IJCAI2021 workshop kicks off today 17 Aug AI For Sports Analytics #AISA Room RED 1 Speakers: @StatsOnTheT @the_spearman et al https://t.co/Y7nm9wS0Yk Something I really enjoy with conferences is learning about mathematical problems directly from people working on solving them. During the week end, I heard about the vertex p-center problem, and loved it.

The 30th International Joint Conference on Artificial Intelligence (IJCAI-21) will run in a virtual format from August 19th to August 26th, 2021. There are a whole host of talks, workshops, tutorials, socials and competitions planned. Find out more about the various events below. An exciting programme of invited talks awaits, with eight speakers from a range of research areas. You can find out more about the speakers and their talks here.