ml-recall

#sparsity

9 questions from Linear Models & Regularization, Logistic Regression & Softmax, Training Deep Networks, Segmentation, Language Modeling

Timed test

9 questions · 9 min · score and explanations at the end

Take a test

Q 1 / 9Score 0 / 0

Shuffle questions

Question 1: Short answer

mediumAI-checkedLinear Models & Regularization

You minimize $L(\mathbf{w}) + \lambda\sum_i |w_i|$ ( $\ell_1$ regularization) by gradient descent with learning rate $\eta = 0.1$ and $\lambda = 0.2$ . A weight has value $w = 0.5$ , and the data loss gives it the gradient $\partial L / \partial w = 0$ . What is $w$ after one update?

Enter: check / next