This paper reviews the application of artificial neural network (ANN)
IntroductionOil quality is a complex issue that is measured by alteration of the physical and chemical composition of organoleptic experiments. Despite the physical and chemical parameters are easily measured, usually they are not directly related to the sensory results. Artificial neural networks have been put in use, in food sciences for more than two decades. ANN is a useful tool for the analysis of quality and food safety, including modeling of health and food safety, spectroscopy data interpretation and quality and performance properties prediction as well as chemical and physical properties of food products during processing and distribution. Modeling is one of the most instrumental tools for rapid and cost-beneficial identification of various system outcomes and process parameters on the output of the process. Nowadays modeling as is a synergetic method for identifying and describing the observed processes and forecasting them under different conditions. Thus, the adverse effect of the process is controlled through having the proper knowledge of how to prevent the occurrence of harms. The theory of artificial neural networks inspired by biological nervous systems of the human brain performs processing operations, so that ANN generation information processors are so powerful that are made of set of internal connections between neurons and acts as a unit and solves and preserves specific complications without any prior knowledge of discovering the intrinsic connection between the data.To analyze the structure of neural networks, it is proved that they are divided into single-layer and multi-layer networks. Layers are composed of three different multilayer neural networks. The existence of three layers to form a neural network is essential. Neurons are constituent elements of the layers in the neural networks. Elements of each layer are associated with all other elements of layers but are not correlated with other elements in