Optimization algorithms are responsible for minimizing losses and providing the most accurate outcomes possible. Optimizers are used to modify neural network parameters, such as training rates and weights, to reduce losses. Optimization is the process of obtaining a global optimal solution for a given problem under specified conditions. Real-world problems in scientific fields, such as engineering design and economic planning, are mostly multimodal, high-dimensional, disconnected, and oscillated optimization problems. These complex problems cannot be efficiently solved using traditional gradient-based methods. Nature-inspired algorithms are increasingly used for mathematical optimization problems like multiprocessor scheduling, vehicle routing, and classification. This manuscript applies the Whale Swarm Optimization algorithm to optimize neural networks, analyzing the cardiovascular disease dataset and comparing performance with Gradient Descent and RMSprop optimization techniques. © 2021 Elsevier B.V., All rights reserved.