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_Quiz2

Riddle

Played 3

About this activity

DL_Riddle_Quiz2

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_Quiz2
 

DL_Riddle_Quiz2Online version

DL_Riddle_Quiz2

by Siva Ranjini
1

I am the year-2015 architecture credited with breaking the "degradation problem" of very deep CNNs

Hints

My block can be written y = F(x) + x.

My deepest published variant on ImageNet had 152 layers and I won ILSVRC 2015 classification.

2

U-Net's encoder doubles the channel count at each downsampling stage, starting at 64.

Hints

After four downsampling stages I am the channel count at the bottleneck.

Compute it: 64 → 128 → 256 → 512 → ?

3

I am the operation that transfers feature maps from the contracting path to the expansive path.

Hints

In the original U-Net paper I am implemented as "copy and crop" because of the unpadded convolutions.

I provide the decoder with high-resolution localisation information that pure upsampling cannot recover

4

I was introduced at MICCAI in 2015 by Ronneberger, Fischer and Brox.

Hints

My architecture has a contracting path and an expansive path that resemble a single English letter.

I was trained on roughly 30 annotated images and won the ISBI cell-tracking challenge.

5

I am a class of generative model trained by setting up a two-player game between two neural networks.

Hints

One of my networks creates fake samples; the other tries to tell real samples from fakes.

My acronym is three letters and I was introduced by Ian Goodfellow and colleagues in 2014.

Are you sure you want to leave the page?

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