— Deep learning continues to be a powerful state-of-art technique that has achieved extraordinary accuracy levels in various domains of regression and classification tasks, including image, signal, and natural language data. The original goal of proposing the neural network model is to improve the understanding of complex human brains using a mathematical approach. However, recent deep learning techniques continue to be difficult to interpret in addition to challenges in explain-ing its functional process. As a result it is being treated mostly as a black-box approximator. Deep learning techniques have continued to steer further and further away from the realistic human brain model, despite its original intents. Such an AI model needs to be biologically and physiologically realistic in order to incorporate a greater understanding of human-machine evolutionary intelligence. In this paper, we compare neural networks with biological mechanisms and physiology to discover the similarities and differences between ANN and what we currently know about the human brain. We also attempt to explain ANNs by exploring human biological behaviors and brain anatomy.