New game
Download
Get Academic Plan
Share game
Integrate it into your platform

You can integrate the game into an LMS compatible with LTI 1.1 or LTI 1.3 such as Canvas, Moodle, or Blackboard. This way, the scores will be automatically saved into the platform’s gradebook.
Download
You have exceeded the maximum number of games you can integrate into Google Classroom with your current Plan.

To integrate as many games as you want in Google Classroom, you need an Academic Plan or a Commercial Plan.

You have exceeded the maximum number of games you can integrate into Microsoft Teams with your current Plan.

To integrate as many games as you want in Microsoft Teams, you need an Academic Plan or a Commercial Plan.

Downloading games is an exclusive feature for users with an Academic Plan or a Commercial Plan.

Get your Academic Plan or your Commercial Plan now and start integrating your games into your LMS, website or blog.

If you wish, you can download a demo game here and test its integration:

DL_Riddle_Quiz 1

Riddle

Played 1

About this activity

DL_RIDDLE_QUIZ_1

Created by

India

Download the paper version to play

Make your own free game from our game creator
Compete against your friends to see who gets the best score in this game

Top Games

%
Anonymous
Anonymous
%
%
%
You have exceeded the maximum number of games you can print with your current Plan.

To print as many games as you want, you need an Academic Plan or a Commercial Plan.

Print your game
DL_Riddle_Quiz 1
 

DL_Riddle_Quiz 1Online version

DL_RIDDLE_QUIZ_1

by Sivaranjini S
1

I am the family of neural networks that operates over hierarchical input defined by a parse tree.

Hints

At every parent node I combine my children using a shared weight matrix.

2

I am the alternative name for a transposed convolution emphasising its mathematical role as the gradient-flow operation of a forward strided convolution.

Hints

I am a misleading term — I am NOT the inverse of convolution and I do NOT recover the original input.

People often use my name even though it is technically incorrect.

3

I am the segmentation loss most directly derived from the F1 score.

Hints

I treat predicted and ground-truth foreground masks symmetrically as sets and penalise their lack of overlap.

I struggle when both masks are empty; people add a small ε to my denominator to avoid division by zero.

4

I am U-Net's mechanism for fusing high-resolution encoder features with upsampled decoder features.

Hints

I do NOT use addition; I append along the channel dimension.

DenseNet is the architecture most associated with applying me densely between every pair of layers in a block.

5

I am a small fully-convolutional network that slides a 3×3 window over a shared backbone feature map.

Hints

I classify each anchor as object/background and regress its bounding-box offset.

I replaced selective search and helped make object detection nearly real-time.

Are you sure you want to leave the page?

If you leave the page, you will lose your game progress.