In this paper we propose the supervised version of neuro-based computational model of brain emotional learning (BEL). In mammalian brain, the limbic system processes emotional stimulus and consists of following two main components: amygdala and orbitofrontal cortex (OFC). Recently several models of BEL based on monotonic reinforcement learning in amygdala are proposed by researchers. Here, we introduce supervised version of BEL which can be learned by pattern-target examples. According to the experimental studies, where various comparisons are made between the proposed method, multilayer perceptron (MLP) and adaptive neuro-fuzzy inference system (ANFIS), the main feature of the presented method is fast training in prediction problems.