Skip to content
ml-recall

#floating-point

8 questions from Optimization & Calculus, Logistic Regression & Softmax, Training Deep Networks, Deep Learning Frameworks, Convolutional Neural Networks, PyTorch, NumPy

Timed test

8 questions · 8 min · score and explanations at the end

Take a test
Q 1 / 8Score 0 / 0

Question 1: Short answer

hardAI-checkedOptimization & Calculus

In float64, the forward difference ((1+h)2−12)/h\big((1 + h)^2 - 1^2\big)/h estimates the derivative of x2x^2 at x=1x = 1, which is 2. What does it return for h=10−15h = 10^{-15}? Round to 2 decimals.

a number, 2 decimals