Learning to learn: From smart machines to intelligent machines
B. Raducanu b a,*
` , J. Vitria
a,b
a Computer Vision Center, Edifici ‘‘O’’ – Campus UAB, 08193 Bellaterra, Barcelona, Spain Computer Science Department, Autonomous University of Barcelona, 08193 Bellaterra, Barcelona, Spain
Available online 14 September 2007
Abstract Since its birth, more than five decades ago, one of the biggest challenges of artificial intelligence remained the building of intelligent machines. Despite amazing advancements, we are still far from having machines that reach human intelligence level. The current paper tries to offer a possible explanation of this situation. For this purpose, we make a review of different learning strategies and context types that are involved in the learning process. We also present the results of a study on cognitive development applied to the problem of face recognition for social robotics. Ó 2007 Elsevier B.V. All rights reserved.
Keywords: Intelligent systems; Cognitive development; Context; Social robotics; Face recognition
1. Introduction The golden dream of artificial intelligence (AI) remains to design and build systems showing human-like intelligence. Nowadays, the machines can perform remarkable things: there are chess algorithms able to play at international masters complexity levels, applications to coordinate the deployment of troops on the battle field, computer aided tools which allow us to design from the most powerful microprocessors to the most sophisticated airplanes. But, on the other hand, despite of the high complexity of the previously mentioned systems, none of them is able to, for instance, interpret the objects that appear in an image, comment a story, answer a question, in general things
