ml-recall

#block-diagonal

1 question from Convolutional Neural Networks

Timed test

1 question · 1 min · score and explanations at the end

Take a test

Q 1 / 1Score 0 / 0

Shuffle questions

Question 1: Short answer

easyAI-checkedConvolutional Neural Networks

A layer multiplies a 256-dimensional channel vector by a dense $256 \times 256$ weight matrix. You replace it with a block-diagonal matrix of 8 blocks of size $32 \times 32$ , as a grouped convolution with 8 groups does. By what factor does the number of multiplications drop?

Enter: check / next