MLE
Maximum Likelihood Estimation is a statistical method for estimating the parameters of a probability distribution that makes the observed data most probable.
Think of It Like This
Like adjusting a telescope's focus knob until the blurry star in your lens looks as sharp and bright as possible.
MLE is the theoretical bedrock for most modern machine learning loss functions. When you train a model to minimize Cross-Entropy loss, you are mathematically performing Maximum Likelihood Estimation. It assumes the training data perfectly represents the true population and does not incorporate prior beliefs.