This study introduces, two models based on Gene Expression Programming (GEP) to predict compressive strength of high strength concrete (HSC). Composition of HSC was assumed simplified, as a mixture of six components (cement, silica fume, super-plastisizer, water, fine aggregate and coarse aggregate). The 28-day compressive strength value was considered the target of the prediction. Data on 159 mixes were taken from various publications. The system was trained based on 80% training pairs chosen randomly from the data set and then tested using remaining 20% samples. Therefore it can be proven and illustrated that the GEP is a strong technique for the prediction of compressive strength amounts of HSC concerning to the outcomes of the training and testing phases compared with experimental outcomes illustrate that the.
