Social robots and agents operate in dynamic social environments where number of users as well as their individual features change over time. In order to be able to identify its users the robot should adapt to the ongoing changes continuously. This paper specifies the problem of concept drift for face identification and proposes a solution based on a modification of online neural network.
CITATION STYLE
Żarkowski, M. (2015). Adaptive online neural network for face identification with concept drift. Advances in Intelligent Systems and Computing, 323, 703–712. https://doi.org/10.1007/978-3-319-11310-4_61
Mendeley helps you to discover research relevant for your work.