Calculus
Gradient descent
Training is just rolling downhill. At each step the model moves against the slope of the loss. The learning rate sets the step size — too big and it overshoots, too small and it crawls.
Steps0
Current loss—
A moderate learning rate slides smoothly to the minimum.
Probability & statistics
Describe your data
Click anywhere on the line to drop a data point. Mean, median, mode, and standard deviation update instantly — see how a few outliers pull the mean away from the median.
Mean—
Median—
Mode—
Std dev—
Points0
When mean and median drift apart, your data is skewed by outliers.