DL_Riddle_Quiz2

Devinette

Parties jouées 3

Créer une copie

À propos de cette activité

DL_Riddle_Quiz2

Créé par

Siva Ranjini

India

Téléchargez la version pour jouer sur papier

Top 10 résultats

Il n'y a toujours pas de résultats pour ce jeu. Soyez le premier à apparaître dans le classement! Connectez-vous pour vous identifier.

Créez votre propre jeu gratuite à partir de notre créateur de jeu

Affrontez vos amis pour voir qui obtient le meilleur score dans ce jeu

Créer un défi

GUESS, GUESSER...

Esteban PedrazaEnciso

Colombia

(10)

¡ I guess the tracks who it is and have fun...!
Fantastic creatures

Educaplay Educational Resources

Spain

(172)

Guess them using as few clues as possible
Words About Words Vocabulary 6c

Ginger Jantz

United States

(13)

Words used to discuss words and writing
The gold riddle

Cody Nakajima

United States

(4)

On your quest you find 3 treasure chests. 1 chest is the gold chest. You need to find the gold chest. But the wrong chests has a deadly gas. And to make matters worse all of the chests look identical....
Brain Game 2

Kecia Hopper

United States

(8)

Brain teasers


DL_Riddle_Quiz2Version en ligne DL_Riddle_Quiz2 par Siva Ranjini 1 I am the year-2015 architecture credited with breaking the "degradation problem" of very deep CNNs Hints 1 My block can be written y = F(x) + x. 2 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 1 After four downsampling stages I am the channel count at the bottleneck. 2 Compute it: 64 → 128 → 256 → 512 → ? 3 I am the operation that transfers feature maps from the contracting path to the expansive path. Hints 1 In the original U-Net paper I am implemented as "copy and crop" because of the unpadded convolutions. 2 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 1 My architecture has a contracting path and an expansive path that resemble a single English letter. 2 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 1 One of my networks creates fake samples; the other tries to tell real samples from fakes. 2 My acronym is three letters and I was introduced by Ian Goodfellow and colleagues in 2014.

DL_Riddle_Quiz2Version en ligne

DL_Riddle_Quiz2

par Siva Ranjini

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.

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 → ?

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

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.

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.

Vous pouvez intégrer le jeu dans un LMS compatible avec LTI 1.1 ou LTI 1.3 comme Canvas, Moodle ou Blackboard. Les scores seront ainsi automatiquement enregistrés dans le carnet de notes de la plateforme.

DL_Riddle_Quiz2

Devinette

À propos de cette activité

Créé par

Téléchargez la version pour jouer sur papier

Top Jeux

Devinette

GUESS, GUESSER...

Devinette

Fantastic creatures

Devinette

Words About Words Vocabulary 6c

Devinette

The gold riddle

Devinette

Brain Game 2

DL_Riddle_Quiz2Version en ligne

par Siva Ranjini

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

Hints

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

Hints

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

Hints

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

Hints

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

Hints

		%
	Anonyme	%
		%
		%