How Much Do You Know About Deep Learning?

You hear a lot about deep learning these days. But how does it actually work?

Take the quiz—just 10 questions—to see how much you know about deep learning!

Start quiz

Question 1/10

What kind of table compares classifications predicted by a model with the actual class labels?

Chaos table

Confusion matrix

Prediction plot

Residual plot

Go to start

Question 2/10

What does hyperparameter tuning do?

Optimizes parameters to improve the performance of a learning algorithm

Specifies the hyperplane that represents linear classifiers

Expands the parameter set of a model to improve performance

Takes parameter tuning so far that performance degrades

Question 3/10

What is overfitting?

When a predictive model is accurate but takes too long to run

When a model learns specifics of the training data that do not generalize well to a new data set

When you apply a powerful deep learning algorithm to a simple machine learning problem

When you perform hyperparameter tuning and performance degrades

Question 4/10

Which of the following is a type of object detection task in which each pixel of an image can be categorized into specific classes?

Regression learning

Sequence classification

Pixel segmentation

Semantic segmentation

Question 5/10

What does a regression model do?

Predicts numeric responses such as changes in temperature, date, or time

Assigns data to a predefined category

Finds patterns by clustering responses in groups based on similarity

Compares predicted data classifications to the actual class labels in the data

Question 6/10

What category of machine learning finds patterns in the data when the data is not labeled?

Data prophecy

Supervised learning

Unsupervised learning

Supervisory logic

Question 7/10

Which of the following networks is commonly associated with synthetic image generation?

Long short-term memory networks

YOLO-v3 networks

Generative adversarial networks

Super resolution networks

Question 8/10

Which of the following describes the process of taking a pretrained neural network and retraining it to classify a new set of images?

Machine learning

Transfer learning

Regression learning

Forecasting

Question 9/10

Which of the following is a deep learning architecture commonly used to classify time series data?

Long short-term memory network

Attention network

Siamese network

Mini-batch algorithms

Question 10/10

What is a validation data set used for?

To test whether a model is superfitting the data

To measure the complexity of a model

To evaluate the model fit after training is complete

To test how well a model generalizes during training

See your results

You scored:
%

It’s a start!

You're just starting to become a deep learning pro. Learn deep learning techniques with the Introducing Deep Learning with MATLAB ebook.

Get the intro ebook

Answer key

Impressive!

You know your stuff! Now master the techniques with MATLAB examples for deep learning.

See examples and resources

Impressive!

You know your stuff! Now master the techniques with Deep Learning Onramp.

Try Deep Learning Onramp

Answer key

You’re a pro!

Start applying these deep learning skills with a free interactive tutorial on deep learning with MATLAB.

Try the Deep Learning Onramp

You’re a pro!

Start applying these deep learning skills with Deep Learning Onramp.

Try Deep Learning Onramp

Answer key

Answer Key

What kind of table compares classifications predicted by a model with the actual class labels? Confusion matrix
What does hyperparameter tuning do? Optimizes parameters to improve performance of a learning algorithm
What is overfitting? When a model learns specifics of the training data that does not generalize well to a new data set
Which of the following is a type of object detection task in which each pixel of an image can be categorized into specific classes? Semantic segmentation
What does a regression model do? Predicts numeric responses such as changes in temperature, date, or time
What category of machine learning finds patterns in the data when the data is not labelled? Unsupervised learning
Which of the following networks is commonly associated with synthetic image generation? Generative adversarial networks
Which of the following is the process of taking a pretrained neural network as a starting point and retrain it to classify a new set of images? Transfer learning
Which of the following is a deep learning architecture commonly used to classify time series data? Long short-term memory network
What is a validation data set used for? To test how well a model generalizes during training

Select a Web Site

Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .

(English)
(Deutsch)
(Français)

（简体中文）
(English)

You can also select a web site from the following list

How to Get Best Site Performance

Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.

Americas

América Latina (Español)
Canada (English)
United States (English)

Europe

Belgium (English)
Denmark (English)
Deutschland (Deutsch)
España (Español)
Finland (English)
France (Français)
Ireland (English)
Italia (Italiano)
Luxembourg (English)

Netherlands (English)
Norway (English)
Österreich (Deutsch)
Portugal (English)
Sweden (English)
Switzerland
United Kingdom (English)

Asia Pacific

Australia (English)
India (English)
New Zealand (English)
中国
- 简体中文
- English
日本 (日本語)
한국 (한국어)

Contact your local office