3-1-5. Dropout:
Dropout [15] is a method employed in deep learning to keep the model
from overfitting to the training data by dropping out neurons randomly
during the training process. The aim is to make the model learn more
generalized features and avoid memorizing the training data. The ratio
of dropped out neurons is a hyperparameter that can be fine-tuned to
achieve the ideal balance between overfitting and underfitting. Dropout
is often combined with other regularization techniques to enhance the
performance of models in computer vision and natural language processing
applications.