We present BL-WoLF, a framework for learnability in repeated zero-sum games where the cost of learning is measured by the losses the learning agent accrues (rather than the number...
Abstract. We present a simple and extendible framework to collect attention metadata and store them for further analysis. Currently, several metadata collectors have been implement...
Maren Scheffel, Martin Friedrich, Katja Niemann, U...
In this paper, we present an automatic web image mining system towards building a universal human age estimator based on facial information, which is applicable to all ethnic grou...
Distance metric learning and nonlinear dimensionality reduction are two interesting and active topics in recent years. However, the connection between them is not thoroughly studi...
Neural networks are a popular technique for learning the adaptive control of non-linear plants. When applied to the complex control of android robots, however, they suffer from se...
Heni Ben Amor, Shuhei Ikemoto, Takashi Minato, Ber...