The special characteristics of plant cell cultures make it difficult to use conventional analytical techniques for on-line biomass monitoring. Meanwhile, promising results have been obtained using mathematical models and recursive estimation algorithms. However, in this case, additional experimental effort is necessary to obtain a reasonable description of the process. Recently, techniques using more empirical approaches have been proposed to describe complex processes, minimizing the experimental work needed for their application. In this paper, we report on the use of artificial neural networks to monitor biomass evolution in plant cell cultures. The results obtained with a three-layered network are presented. Method requirements and capabilities are compared with the method based on the extended Kalman filter used in previous work.