wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

LSTM_Module_6

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

What is the purpose of regression in machine learning?

a)

To classify images into categories

b)

To predict a continuous value based on input variables

c)

To detect objects in an image

d)

None of the above

2.

Which of the following is the key assumption in linear regression?

a)

The relationship between variables is non-linear

b)

The dependent variable is categorical

c)

There is a linear relationship between the dependent and independent variables

d)

The data is not normally distributed

3.

Which of the following is true about ARIMA (AutoRegressive Integrated Moving Average)?

a)

ARIMA is used for classifying objects in an image

b)

ARIMA requires stationary time series data

c)

ARIMA is only used for supervised learning tasks

d)

ARIMA is used to predict continuous variables but not time series data

4.

What does the VAR (Vector Autoregressive) model help with in time series analysis?

a)

Predicting a single time series variable

b)

Capturing the relationships between multiple time series variables

c)

Performing classification tasks

d)

None of the above

5.

Which of the following is a characteristic of LSTM (Long Short-Term Memory) networks?

a)

They are used for object detection

b)

They are designed to handle sequential data and learn long-term dependencies

c)

They are used for clustering tasks

d)

None of the above

6.

What type of data is ARIMA most suitable for?

a)

Unstructured data like images or text

b)

Categorical data

c)

Time series data that shows trends or patterns over time

d)

None of the above

7.

Which of the following is used to evaluate the performance of linear regression?

a)

Confusion matrix

b)

RMSE

c)

Precision and recall

d)

F1 score

8.

In LSTM networks, what are the three key components that control the flow of information?

a)

Forget gate, input gate, and output gate

b)

Recurrent gate, input gate, and hidden gate

c)

Activation gate, input gate, and output gate

d)

Non input gate, and output gate and hidden gate

9.

Which model is used for long-term forecasting of sequential data with long-term dependencies?

a)

Linear regression

b)

ARIMA

c)

LSTM

d)

VAR

10.

Which of the following manufacturing applications would benefit most from using a regression model?

a)

Predicting the quality of a product based on machine parameters

b)

Identifying faulty parts on an assembly line

c)

Classifying types of products based on images

d)

Detecting workers not wearing safety gear

11.

In a manufacturing process, which scenario is best suited for a regression model?

a)

Predicting the total production cost based on raw material usage and labor hours

b)

Detecting the presence of defects in products

c)

Identifying the category of products in a warehouse

d)

Counting the number of items in a batch

12.

In an LSTM network, what is the primary function of the forget gate?

a)

It decides which information should be remembered

b)

It regulates the learning rate during training

c)

It decides which information from the input should be discarded

d)

It helps in the backpropagation of errors

13.

What is the main advantage of using LSTM networks for time-series forecasting?

a)

They can process data in parallel for faster computation

b)

They can learn long-term dependencies in sequential data

c)

They perform better with unsupervised learning tasks

d)

They do not require any prior data preprocessing

14.

In an LSTM network, which of the following gates controls the flow of new information into the memory cell?

a)

Forget gate

b)

Input gate

c)

Activation gate

d)

Hidden gate

15.

What type of data is LSTM most suitable for?

a)

Image classification tasks

b)

Sequential or time-series data such as stock prices or weather patterns

c)

Static data where the order does not matter

d)

Non-time-dependent features

16.

What is the purpose of tuning hyperparameters in machine learning models?

a)

To improve the model's training time

b)

To find the best configuration for model performance

c)

To ensure the model runs faster on hardware

d)

To reduce the amount of data needed for training

17.

What does the term "epochs" refer to in machine learning?

a)

The amount of data used for validation

b)

The number of features in the dataset

c)

The number of iterations in a single forward pass

d)

The number of times the entire dataset is passed through the model during training

18.

What does RMSE (Root Mean Squared Error) measure in a machine learning model?

a)

The average error between predicted and actual values

b)

The square of the error between predicted and actual values

c)

The square root of the average squared differences between predicted and actual values

d)

The sum of the absolute errors between predicted and actual values

19.

What is the primary goal of multi-ahead time forecasting in machine learning?

a)

To predict only the next data point in a time series

b)

To predict multiple future data points for a given time horizon

c)

To classify data into different categories

d)

To generate synthetic data points for model training

20.

In the context of manufacturing, which of the following best describes the primary use cases for CNN, YOLO, and LSTM?

a)

CNN is used for detecting machine faults based on vibration data, YOLO is used for real-time detection of defective products, and LSTM is used for forecasting equipment maintenance schedules based on historical data

b)

CNN is used for identifying product defects in images, YOLO is used for detecting workers wearing safety gear, and LSTM is used for predicting production demand based on past trends

c)

CNN is used for classifying different product types on an assembly line, YOLO is used for tracking inventory, and LSTM is used for monitoring machine temperature in real-time

d)

CNN is used for real-time monitoring of production lines, YOLO is used for predicting the total cost of production, and LSTM is used for detecting raw material shortages