DL_Froggy Jump_Quiz2

Froggy Jumps

Played 2

Create copy

About this activity

Choose the correct option

Created by

Siva Ranjini

India

Download the paper version to play

Top 10 results

There are still no results for this game. Be the first to stay in the ranking! Log in to identify yourself.

Make your own free game from our game creator

Compete against your friends to see who gets the best score in this game

Make challenge

The Integumentary System

Breanna Nesbitt

United States

(58)

Functions and Structures of the skin
pizza

Lorelay Tyana

Romania

(261)

joc despre pizza
Ethos, Pathos, and Logos Quiz

Kristine Vester

United States

(131)

Test your knowledge of ethos, pathos, and logos with these 10 questions on examples of persuasive techniques.
Phlebotomy Order of Draw Quiz

Pamela Chapman

United States

(59)

Test your knowledge of the order of draw in Phlebotomy with these 10 questions!
Bill of Rights Game - The Constitutionalist

Doni The Don

United States

(90)

Test your knowledge on the Bill of Rights. A fun way to test your knowledge and focus on where you need to improve.


Froggy Jumps DL_Froggy Jump_Quiz2Online version Choose the correct option by Siva Ranjini 1 ResNet won which competition in 2015? a ImageNet ILSVRC 2015 classification (and also the COCO 2015 detection challenge) b PASCAL VOC 2015 detection c The MICCAI BraTS 2015 challenge 2 When the input and output dimensions of a residual block differ (because of a channel change or spatial downsampling), the shortcut path uses: a A 1×1 convolution to project to the new dimensions b Zero-padding only and no learned parameters c The block is skipped entirely 3 The two main families of skip connection in modern deep learning are: a Additive and concatenative b Forward and backward c Linear and non-linear 4 In Faster R-CNN, the output of RoI Pooling is most directly fed into: a Two parallel heads — a softmax class classifier and a bounding-box regressor b A non-maximum suppression block c The Region Proposal Network 5 Which loss is most often added to categorical cross-entropy specifically to combat class imbalance in segmentation (foreground ≪ background)? a Focal loss or Dice loss b L2 / mean-squared error c Hinge loss 6 How many resolution levels does the original U-Net's contracting path have, including the bottleneck? a 5 b 6 c 3 7 The defining innovation of ResNet (He et al., 2015) is: a Adding identity skip connections, the block output is F(x) + x b Using only 1×1 convolutions throughout the network c Replacing ReLU with a smoother activation

Froggy Jumps

DL_Froggy Jump_Quiz2Online version

Choose the correct option

by Siva Ranjini

ResNet won which competition in 2015?

ImageNet ILSVRC 2015 classification (and also the COCO 2015 detection challenge)

PASCAL VOC 2015 detection

The MICCAI BraTS 2015 challenge

When the input and output dimensions of a residual block differ (because of a channel change or spatial downsampling), the shortcut path uses:

A 1×1 convolution to project to the new dimensions

Zero-padding only and no learned parameters

The block is skipped entirely

The two main families of skip connection in modern deep learning are:

Additive and concatenative

Forward and backward

Linear and non-linear

In Faster R-CNN, the output of RoI Pooling is most directly fed into:

Two parallel heads — a softmax class classifier and a bounding-box regressor

A non-maximum suppression block

The Region Proposal Network

Which loss is most often added to categorical cross-entropy specifically to combat class imbalance in segmentation (foreground ≪ background)?

Focal loss or Dice loss

L2 / mean-squared error

Hinge loss

How many resolution levels does the original U-Net's contracting path have, including the bottleneck?

The defining innovation of ResNet (He et al., 2015) is:

Adding identity skip connections, the block output is F(x) + x

Using only 1×1 convolutions throughout the network

Replacing ReLU with a smoother activation

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.

DL_Froggy Jump_Quiz2

Froggy Jumps

About this activity

Created by

Download the paper version to play

Top Games

Froggy Jumps

The Integumentary System

Froggy Jumps

pizza

Froggy Jumps

Ethos, Pathos, and Logos Quiz

Froggy Jumps

Phlebotomy Order of Draw Quiz

Froggy Jumps

Bill of Rights Game - The Constitutionalist

Froggy Jumps

DL_Froggy Jump_Quiz2Online version

by Siva Ranjini

ResNet won which competition in 2015?

When the input and output dimensions of a residual block differ (because of a channel change or spatial downsampling), the shortcut path uses:

The two main families of skip connection in modern deep learning are:

In Faster R-CNN, the output of RoI Pooling is most directly fed into:

Which loss is most often added to categorical cross-entropy specifically to combat class imbalance in segmentation (foreground ≪ background)?

How many resolution levels does the original U-Net's contracting path have, including the bottleneck?

The defining innovation of ResNet (He et al., 2015) is:

		%
	Anonymous	%
		%
		%