Scribd
Upload
16 views2 pages

Question Bank for Deep Learning

The document is a question bank focused on deep learning, covering topics such as neural networks, information theory, training methods, and TensorFlow. It includes questions on activation functions, loss functions, gradient descent, and concepts like overfitting and underfitting. Additionally, it discusses the differences between TensorFlow versions and the importance of test and validation sets in machine learning.

Uploaded by

aditya0314n
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
16 views2 pages

Question Bank for Deep Learning

The document is a question bank focused on deep learning, covering topics such as neural networks, information theory, training methods, and TensorFlow. It includes questions on activation functions, loss functions, gradient descent, and concepts like overfitting and underfitting. Additionally, it discusses the differences between TensorFlow versions and the importance of test and validation sets in machine learning.

Uploaded by

aditya0314n
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Question Bank for Deep Learning

Neural Network and Information Theory


1. What is the difference between Machine Learning and Deep Learning?
2. List the commonly used activation functions and their purpose.
3. Compare sigmoid and ReLU activation functions. Highlight their advantages and
disadvantages.
4. Compare sigmoid and tanh activation functions. Highlight their advantages and
disadvantages.
5. Define Shannon Entropy and its significance in information theory.
6. What is loss(cost or error function)? What are different types of loss functions?
7. Explain the architecture of a deep feed-forward neural network. How does it differ
from a shallow feed-forward neural network?
8. Discuss the differences between shallow and deep feed-forward neural networks.
9. What is a perceptron? Explain its limitations.
10. Why is the softmax function used in the output layer of a neural network?
11. Explain Kullback-Leibler divergence with an example. Given two probability
distributions, P = [0.6, 0.4] and Q = [0.5, 0.5], calculate the KL Divergence between P
and Q.
12. What is Information Theory? Explain with suitable example.

Training Neural Network

1. What is gradient descent, and why is it used in neural network training?


2. Define learning rate. How does it affect the training process?
3. What is the delta rule, and how is it related to learning rate?
4. Explain the role of derivatives in neural network optimization.
5. Differentiate between batch gradient descent and stochastic gradient descent.
6. Explain the purpose of mini-batch gradient descent

TensorFlow
1. What is lazy execution in TensorFlow 1.x? How is it different from Eager execution.
Explain with example.
2. What are tensors? Explain the different types of tensors with suitable examples.
3. What are the different versions of TensorFlow? How TensorFlow 2.x different from
TensorFlow 1.x?
4. Discuss the concept of computation graphs in TensorFlow 1.x.
5. What is overfitting and underfitting? How can we overcome overfitting in our deep
learning model?
6. What is a test set? How does it differ from validation set? Why are they necessary in
building machine learning models?
7. What are the steps to be followed in building machine learning models? Elaborate.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy