You're tasked with building a calculator application. Which approach would be the most suitable?

Traditional programming, as it involves clear rules and logic

ML guy notices their image classification model performs well on the test set but poorly on real-world images. Reason?

Mismatch between training and real-world data distribution

What is the purpose of dividing a dataset into training and testing sets in machine learning?

To ensure the model can generalize well to unseen data

Which of the following best describes the difference between traditional programming (TP) and machine learning (ML)?

TP uses explicit rules to solve problems, while ML uses data

Which of the following statements is true about machine learning models?

A model should be evaluated using both training and testing data.

Which of the following situations is likely to produce CONTINUOUS data?

Measuring the amount of rainfall in a city

A key advantage of machine learning over traditional programming is:

ML can adapt and improve performance over time when exposed to more data

Which of the following is an example of DISCRETE data?

The number of students in a classroom

In the context of machine learning, what is overfitting?

A model performs well on the training data but poorly on the testing data

What does the concept of Bias-Variance Tradeoff relate to?

The balance between underfitting and overfitting in machine learning models

studbud

Duplicate of Class_2_3_SML

18 termsStudBud Administration

Imported from external platform

Flashcards18 cardsFPractice quizPHost liveL

Questions 18

Answers

1
You're tasked with building a calculator application. Which approach would be the most suitable?
Both traditional programming and machine learning are equally suitable
Machine learning, as it can learn from user input patterns
Traditional programming, as it involves clear rules and logic
Neither, a different approach is needed entirely
2
You want to group customers into clusters based on their purchasing behavior, Which type of ML use?
Unsupervised learning
Supervised learning
Deep learning
Reinforcement learning
3
ML guy notices their image classification model performs well on the test set but poorly on real-world images. Reason?
Errors in the programming code
Inadequate model complexity
Insufficient training time
Mismatch between training and real-world data distribution
4
In an experiment investigating the effect of fertilizer on plant growth, which of the following is INDEPENDENT variable?
The type of plant
The amount of fertilizer used
The height of the plants
The amount of sunlight received
5
What is the purpose of dividing a dataset into training and testing sets in machine learning?
To ensure the model can generalize well to unseen data
To make the training process faster
To reduce the need for data cleaning
To increase the size of the dataset
6
Which of the following best describes the difference between traditional programming (TP) and machine learning (ML)?
TP relies on human expertise, while ML focuses on automation
TP uses explicit rules to solve problems, while ML uses data
TP is faster to develop, while MLrequires more time and dat
TP is used for web development, while ML is used for image recognition
7
Which of the following statements is true about machine learning models?
The best machine learning model always has the most complex structure.
Overfitting occurs when a model generalizes well to new data.
A model should be evaluated using both training and testing data.
A model fits the training data well will always perform well on new data.
8
Which of the following situations is likely to produce CONTINUOUS data?
Tracking the number of votes cast in an election
Recording the number of books on a library shelf
Measuring the amount of rainfall in a city
Counting the number of cars passing through an intersection
9
Which type of ML is used when you have labeled data (i.e., you know the target outcome you want to predict)?
Unsupervised learning
Semi-supervised learning
Supervised learning
Reinforcement learning
10
A key advantage of machine learning over traditional programming is:
Machine learning is easier to learn and implement for beginners
Machine learning guarantees perfect accuracy in its outputs
Machine learning does not require any human intervention
ML can adapt and improve performance over time when exposed to more data
11
A self-driving car learns to improve its driving based on rewards and penalties. What type of ML is this?
Unsupervised learning
Supervised learning
Batch learning
Reinforcement learning
12
Which type of machine learning uses a combination of labeled and unlabeled data?
Semi-supervised learning
Reinforcement learning
Supervised learning
Unsupervised learning
13
You're conducting a survey and ask participants to report their age. This data will be:
discrete or continuous, depending on how the question is worded
Discrete
Neither discrete nor continuous
Continuous
14
Which of the following is an example of DISCRETE data?
The time it takes to run a marathon
The weight of a newborn baby
The number of students in a classroom
The temperature of a swimming pool
15
Which of the following is a challenge associated with clustering?
Determining the optimal number of clusters.
Handling noisy data or outliers.
All of the above.
The results can be subjective and depend on the similarity measure used.
16
In the context of machine learning, what is overfitting?
A model requires more data to improve its accuracy
A model is too simple to capture the underlying pattern of the data
The training and testing datasets are identical
A model performs well on the training data but poorly on the testing data
17
A researcher wants to study whether sleep deprivation impacts test scores. Here, the DEPENDENT variable would be:
The difficulty of the test
The test scores
The age of the participants
The number of hours of sleep
18
What does the concept of Bias-Variance Tradeoff relate to?
The difference between training and testing data
The tradeoff between model complexity and runtime efficiency
The process of selecting the best machine learning algorithm
The balance between underfitting and overfitting in machine learning models

Duplicate of Class_2_3_SML Flashcards | StudBud