Scribd
Upload
5 views

Assignment - Intro to Deep Learning

The document outlines an assignment designed to evaluate foundational knowledge of deep learning through multiple-choice questions (MCQs). It covers various aspects of deep learning, including its applications, key components, challenges, and evaluation metrics. The assignment consists of 10 MCQs aimed at testing understanding of deep learning principles and practices.

Uploaded by

ankitayadav8065
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
5 views

Assignment - Intro to Deep Learning

The document outlines an assignment designed to evaluate foundational knowledge of deep learning through multiple-choice questions (MCQs). It covers various aspects of deep learning, including its applications, key components, challenges, and evaluation metrics. The assignment consists of 10 MCQs aimed at testing understanding of deep learning principles and practices.

Uploaded by

ankitayadav8065
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Introduction: Deep learning, a subset of machine learning, has

revolutionized the field of artificial intelligence by enabling machines to


learn from data in a way that mimics human learning at a fundamental
level. As this technology continues to advance, it becomes increasingly
important for professionals to grasp the core principles that underpin deep
learning algorithms and architectures.
The objective of this assignment is to evaluate the foundational knowledge
of deep learning through a series of carefully crafted multiple-choice
questions (MCQs). These questions are designed to test various aspects of
deep learning, including its history, fundamental concepts, key
architectures, and the underlying mathematics. The MCQ format is chosen
for its ability to assess a wide range of topics succinctly and to provide
immediate feedback on the learner's understanding.

The assignment consists of 10 MCQs, each with a single or multiple


correct answers.

1. Which industries commonly use Deep Learning for image recognition


applications?
a. Healthcare
b. Manufacturing
c. Retail
d. All of the above

2. What distinguishes Deep Learning from traditional Machine Learning?


a. Depth of Neural Networks
b. Type of Algorithms used
c. Machine Learning is an evolution of Deep Learning
d. Volume of data processed
i. a,d Answer is a & d
ii. a,b,c,d
iii. a,c,d
iv. a,b

3. Which metrics are commonly used to evaluate the performance of a


classification model?
a. Mean squared error
b. Root mean squared error
c. F1 score
d. R-squared

4. Which of the following are the key components of Deep Learning (DL)?
a. Decision Trees
b. Neural Networks
c. Support Vector Machines
d. K-Means Clustering

5. What are the main challenges in training deep neural networks?


a. Lack of labelled data
b. Overfitting
c. Underfitting
d. None of the above
Answer is: a,b and c all three
6. Which technology is a subset of AI and focuses on training models to
learn from data?
a. Artificial Intelligence
b. Machine Learning
c. Deep Learning
d. Data Science

7. In the context of Deep Learning, what is a neural network?


a. A network of interconnected computers
b. A network of interconnected neurons
c. A network of interconnected databases
d. A network of interconnected algorithms

8. What is the role of hyperparameter tuning in the model evaluation


phase?
a. To adjust the learning rate
b. To optimize model parameters for better performance
c. To select features
d. To preprocess the data

9. What is the primary goal during the project initiation phase of a Deep
Learning
project?
a. Model training
b. Define the problem and scope
c. Hyperparameter tuning
d. Data collection

10. Why is continuous monitoring important in the life cycle of a deployed


Deep Learning model?
a. To retrain the model from scratch
b. To ensure the model adapts to changing data patterns
c. To deploy a new model version daily
d. To skip the model evaluation phase

You might also like