The human nervous system utilizes synaptic plasticity to solve optimizationproblems. Previous studies have tried to add the plasticity factor to thetraining process of artificial neural networks, but most of those modelsrequire complex external control over the network or complex novel rules. Inthis manuscript, a novel nature-inspired optimization algorithm is introducedthat imitates biological neural plasticity. Furthermore, the model is tested onthree datasets and the results are compared with gradient descent optimization.