With A Tail of Cat Food Preferences
Welcome to the ‘Courage to learn ML’. This series goals to simplify complex machine learning concepts, presenting them as a relaxed and informative dialogue, very similar to the engaging kind of “The Courage to Be Disliked,” but with a deal with ML.
On this installment of our series, our mentor-learner duo dives right into a fresh discussion on statistical concepts like MLE and MAP. This discussion will lay the groundwork for us to realize a brand new perspective on our previous exploration of L1 & L2 Regularization. For a whole picture, I like to recommend reading this post before reading the fourth a part of ‘Courage to Learn ML: Demystifying L1 & L2 Regularization’.
This text is designed to tackle fundamental questions that may need crossed your path in Q&A mode. As at all times, if you happen to end up have similar questions, you’ve come to the correct place:
- What exactly is ‘likelihood’?
- The difference between likelihood and probability
- Why is likelihood vital within the context of machine learning?
- What’s MLE (Maximum Likelihood Estimation)?
- What’s MAP (Maximum A Posteriori Estimation)?
- The difference between MLE and Least square
- The Links and Distinctions Between MLE and MAP
Likelihood, or more specifically the likelihood function, is a statistical concept used to judge the probability of observing the given data under various sets of model parameters. It is named likelihood (function) since it’s a function that quantifies how likely it’s to look at the present data for various parameter values of a statistical model.
The concepts of likelihood and probability are fundamentally different in statistics. Probability measures the prospect of observing a selected consequence in the long run, given known parameters or distributions…