Estimating reservoir petrophysical parameters such as porosity, permeability, water and oil saturation is vital to any in-situ hydrocarbon reserve evaluation. In the case of highly heterogeneous reservoirs (common states of most Iranian oil reservoirs), prediction of these parameters is not only complicated but in some cases is a serious challenge to the upstream oil industries. The conventional means of estimating these parameters is measuring them via core samples taken from wells in the laboratory. Although laboratory methods of estimating petrophysical parameters is still a common practice but the problem of being costly and more time-consuming is not significantly resolved yet. With the development of new generation well logging tools and systems, the cost of estimating these parameters through well log data has significantly decreased. However due to being indirect estimator and dependent on some other environmental variables, it is a necessity to employ state of the art intelligence methods of estimating and predicting techniques to improve their accuracy and effectiveness compared to measurements made on core samples. Determination of lithology and petrophysical parameters of reservoirs using different well logs has become the central part of any petroleum exploration and development program in oil and gas upstream industry. In the current study, the horizontal porosity and permeability as the most important petrophysical parameters of Asmari reservoir formation in Ahvaz oil field have been estimated using four versions of intelligent techniques called conventional artificial neural networks, artificial neural networks based on PCA transformation, statistical neural networks based on bootstrapping and combined neural and fuzzy logic approach called neurofuzzy inference networks. The Ahvaz oil field forms an anticline structure striking parallel to the Zagros ranges and is located in the south to southwest of Dezful Embayment extending 67 by 6km in length and width respectively. Data preprocessing including removing outlier data and multivariate statistical analysis between input and output data were carried out in order to understand the variational behavior and patterns among multivariate data. Well log data including log depth, caliper, conductivity, sonic, natural gamma, density and neutron on one hand and estimated parameters such as water saturation, percent of shale volume and type of lithology as interpreted geological inputs on other hand were used as the input of neural network predictors of drilled core horizontal porosity and permeability taken?? from a total number of 19 exploratory cored wells. The above input-output data have been used to optimize the designed network through training, validating and testing different artificial neural networks explained earlier.