diff --git a/README.md b/README.md index 625d16f543609f379e5663f2a939d6af140bd91c..71523403173d7cb32e06594544a4837de4817ecd 100644 --- a/README.md +++ b/README.md @@ -38,7 +38,7 @@ To illustrate: Suppose a line in `solution.txt` is: ``` If the corresponding line in `predict.txt` is also 1 0 0, then it's a correct prediction. Conversely, if the corresponding line in `predict.txt` is 0 1 0 or 1 0 1 (or any sequence other than 1 0 0), then it's an incorrect prediction. -* Mean squared error(MSE): It quantifies the difference between the predicted values and the actual values. For each line, the squared difference between the numbers in `solution.txt` and `predict.txt` is computed and then averaged over all lines. The formula for MSE is: +* **Mean squared error(MSE)**: It quantifies the difference between the predicted values and the actual values. For each line, the squared difference between the numbers in `solution.txt` and `predict.txt` is computed and then averaged over all lines. The formula for MSE is: $$ MSE = \frac{1}{N} \sum_{i=1}^{N} (predicted_i - actual_i)² $$ Where $N$ is the total number of predictions. @@ -46,7 +46,8 @@ Suppose, for a particular line: * `solution.txt` has: 1 0 0 * `predict.txt` has: 1 1 0 -So, for this line, the squared error is $ (1 - 1)² + (1 - 0)² + (0 - 0)² = 1 $. Note that the MSE between two files would be the average of the squared errors for all lines. +So, for this line, the squared error is $$ (1 - 1)² + (1 - 0)² + (0 - 0)² = 1 $$ +Note that the MSE between two files would be the average of the squared errors for all lines. ## Role-playing