Test Oracle is a mechanism to determine if an application executed correctly. In addition, it may be difficult to verify logical software modules due to the complexity of their structures. In this paper, an attempt has been made to study the applications of Artificial Neural Networks as Single-Network Oracles to verify logical modules. First, the logical module under test was modeled by the neural network using a training dataset generated based on the software specifications. Next, the proposed approach was applied to test a subject-registration application; meanwhile, the quality of the proposed oracle is measured by assessing its accuracy, precision, misclassification error and practicality in practice, using mutation testing by implementing two different versions of the case study: a Golden Version and a Mutated Version. The results indicate that neural networks may be reliable and applicative as oracles to verify logical modules.