Introduction: Physics-Informed Neural Networks (PINNs) represent a powerful deep learning paradigm that seamlessly integrates domain-specific knowledge into machine learning models, enabling an accurate and efficient solution of complex physics-based problems. This research builds upon the foundations laid by [1], showcasing the potential of PINNs in fluid dynamics, and aligns with the growing discourse on the intersection of machine learning and physics, as exemplified by [2]. This study explores the application of PINNs in the context of solving complex nonlinear partial differential equations (PDEs) within the realm of fluid dynamics. Methodology: Focusing on the broader landscape of computational physics, we provide an approach for the application of PINN architecture capable of capturing the behavior of fluid flow without explicit knowledge of the underlying Burgers equation. Developed solution is then compared to the already existing numerical solution at three distinctive time points 0.25; 0.5 and 0.75. Results: The results demonstrate the efficacy of these PINN models in predicting fluid dynamics with a reduced need for domain-specific knowledge, as there is a good match between the PINN and numerical solutions. The integration of physics principles into the training process enhances the interpretability and reliability of the neural network predictions. Conclusions and Significance: By harnessing the power of data-driven insights, we contribute to the efficient and accurate modeling of nonlinear systems. The synergy between data-driven modeling and physics-informed constraints presents a novel approach to unraveling the complexities inherent in nonlinear transport phenomena.