Skip to content
ml-recall

#global-average-pooling

4 questions from Convolutional Neural Networks, Landmark Architectures

Timed test

4 questions · 4 min · score and explanations at the end

Take a test
Q 1 / 4Score 0 / 0

Question 1: Short answer

mediumAI-checkedConvolutional Neural Networks

A convolutional base outputs 512 feature maps of size 5×55 \times 5 per image, and the head is a single Dense(1, activation='sigmoid') unit. That unit has trainable parameters if the maps are flattened first, and if they first go through global average pooling.

Fill in every blank (hints in the boxes). Enter moves to the next blank.