Apply the same exact min-max rule to every displayed row.

highlighted = computed this step

Scale candidate A

A=(1,0) becomes (1/4, 0). Both entries come from the same min and max table.

Ascaled=(1/4,0)A_{\text{scaled}}=(1/4,0)
Feature Scaling ExactlyExact min-max fractions from one displayed table.min-max scaled feature tablerowsmall rawlarge rawsmall scaledlarge scaledQ09009/10A101/40B410011small: min 0, max 4, range 4large: min 0, max 100, range 100preprocessing changes coordinate scale onlydistance and gradient-style methods see the changed coordinatesNOT training; NOT learning; NOT generalizationNOT accuracy; NOT calibration; NOT a guarantee of model qualityNOT probability truth

Scale candidate B

B=(4,100) is at both maxima, so it becomes (1, 1).

Bscaled=(1,1)B_{\text{scaled}}=(1,1)
Feature Scaling ExactlyExact min-max fractions from one displayed table.min-max scaled feature tablerowsmall rawlarge rawsmall scaledlarge scaledQ09009/10A101/40B410011small: min 0, max 4, range 4large: min 0, max 100, range 100preprocessing changes coordinate scale onlydistance and gradient-style methods see the changed coordinatesNOT training; NOT learning; NOT generalizationNOT accuracy; NOT calibration; NOT a guarantee of model qualityNOT probability truth

The rows did not change identity

Q, A, and B are the same displayed rows. Only the coordinate scale was rewritten with exact fractions.

same row labels; exact scaled fractions\text{same row labels; exact scaled fractions}
Feature Scaling ExactlyExact min-max fractions from one displayed table.min-max scaled feature tablerowsmall rawlarge rawsmall scaledlarge scaledQ09009/10A101/40B410011small: min 0, max 4, range 4large: min 0, max 100, range 100preprocessing changes coordinate scale onlydistance and gradient-style methods see the changed coordinatesNOT training; NOT learning; NOT generalizationNOT accuracy; NOT calibration; NOT a guarantee of model qualityNOT probability truth