TASK-DEPENDENT LEARNING OF ATTENTION

In this article, we propose a neural network model for selective cover t visual attention. This model can learn to focus its attention on imp ortant features depending on the task to be fulfilled by gating the fl ow of information from the lower to the higher levels of the visual sy stem. The model is kept as simple as possible, but it is still capable of reproducing attentional behavior observed in psychological experim ents. Computer simulations demonstrate that (1) it can learn categorie s to reduce reaction time without a decrease in performance, (2) the m odel reveals a performance similar to that of humans in feature and co njunction search, and (3) its learning dynamics are comparable with th ose of humans. (C) 1997 Elsevier Science Ltd.