Evaluation in artificial intelligence: From task-oriented to ability-oriented measurement

The final publication is available at Springer via http://dx.doi.org/ 10.1007/s10462-016-9505-7.The evaluation of artificial intelligence systems and components is crucial for the progress of the discipline. In this paper we describe and critically assess the different ways AI systems are evaluated, and the role of components and techniques in these systems. We first focus on the traditional task-oriented evaluation approach. We identify three kinds of evaluation: human discrimination, problem benchmarks and peer confrontation. We describe some of the limitations of the many evaluation schemes and competitions in these three categories, and follow the progression of some of these tests. We then focus on a less customary (and challenging) ability-oriented evaluation approach, where a system is characterised by its (cognitive) abilities, rather than by the tasks it is designed to solve. We discuss several possibilities: the adaptation of cognitive tests used for humans and animals, the development of tests derived from algorithmic information theory or more integrated approaches under the perspective of universal psychometrics. We analyse some evaluation tests from AI that are better positioned for an ability-oriented evaluation and discuss how their problems and limitations can possibly be addressed with some of the tools and ideas that appear within the paper. Finally, we enumerate a series of lessons learnt and generic guidelines to be used when an AI evaluation scheme is under consideration.I thank the organisers of the AEPIA Summer School On Artificial Intelligence, held in September 2014, for giving me the opportunity to give a lecture on 'AI Evaluation'. This paper was born out of and evolved through that lecture. The information about many benchmarks and competitions discussed in this paper have been contrasted with information from and discussions with many people: M. Bedia, A. Cangelosi, C. Dimitrakakis, I. GarcIa-Varea, Katja Hofmann, W. Langdon, E. Messina, S. Mueller, M. Siebers and C. Soares. Figure 4 is courtesy of F. Martinez-Plumed. Finally, I thank the anonymous reviewers, whose comments have helped to significantly improve the balance and coverage of the paper. This work has been partially supported by the EU (FEDER) and the Spanish MINECO under Grants TIN 2013-45732-C4-1-P, TIN 2015-69175-C4-1-R and by Generalitat Valenciana PROMETEOII2015/013.José Hernández-Orallo (2016). Evaluation in artificial intelligence: From task-oriented to ability-oriented measurement. Artificial Intelligence Review. 1-51. doi:10.1007/s10462-016-9505-7S15