Diabetes is one of metabolic diseases where a patient has high blood sugar either caused by the body failure to produce enough insulin or the cells failure to respond to the produced insulin. Diabetes can be identified by studying on several readings taken from a patient such as fasting glucose, sodium, potassium, urea, creatinine, albumin and many others. This paper presents a study on the prediction of diabetes with different supervised learning algorithms of Artificial Neural Network. Fletcher-Powell Conjugate Gradient, Polak-Ribiére Conjugate Gradient and Scaled Conjugate Gradient algorithms are used for diabetes prediction with the collected data. The network is trained using the data of 250 diabetes patients between 25 to 78 years old. Discussion on the performance of each algorithm is provided by performing regression analysis to investigate the correlation between the predicted and target results. The values of correlation coefficient, R of the algorithms are compared to determine the best algorithm for the diabetes prediction task.