In recent years, Artificial Neural Network (ANN) modeling has received a great attention in engineering community and; it has been used extensively in geotechnical engineering applications. The ANN models have been generally used for the solution of complex engineering problems. The objective of this study is to develop ANN models for estimating unconfined compressive strength (qu) of cohesive soils using SPT-N value with index properties in Turkey. The performance of the ANN models is investigated using different input variables such as measured N (Nfield), corrected N (N60) value, natural water content (wn), liquid limit (wL), plasticity index (Ip) and effective vertical stress (σv′). A feed forward back-propapagation algorithm is applied in the analyses. The predictions of the various developed ANN models are compared with the corresponding actual values. It is shown that the developed ANN models give more reliable predictions in terms of estimating qu values, and thus they can be used as a tool to estimate qu