Upper_Bounds_for_Bayes_Error_Questions_and_comment

Please leave me comment below if you have any questions, if you notice any errors or if you would like to discuss a topic further.

Questions and Comments

Varun Vasudevan Review: This slecture on the “Upper Bounds for Bayes' Error” is concise and has good visuals. Dilshan starts with Bayes' rule for the continuous case and arrives at the formula for computing the probability of error in the classification. He provides intuition through a two-class classification example. He then computes the upper bound for the probability of error for a general distribution which is followed by expressions for the normally distributed case. Explanation has been provided for the different terms that appear in the expression for the bound. He also mentions about the special case, when beta = 0, which gives the Bhattacharyya bound.

The slecture is self-contained and, I like the style of writing. A few suggestions for making this slecture “The Best” would be:
- Could provide few lines of explanation on the second figure since it is not clear in the first reading.
- Might want to mention why solving for the integral in the expression for probability of error is intractable.
- X-axis for the first figure is missing. Check for typos. In LaTeX, while using double quotes at the beginning of a sentence you should be using ``, i.e., the Shift + <the key to the left of 1 on your keyboard>