Scribd
Upload
4 views2 pages

Deep Learning Important Questions

The document outlines important questions for a semester-end examination on Deep Learning Techniques at JNTU Kakinada, covering five units. Each unit consists of three questions focusing on topics such as the fundamentals of deep learning, neural networks, CNN and RNN architectures, and applications in machine vision and natural language processing. The questions aim to assess students' understanding of key concepts, architectures, and tools in deep learning.

Uploaded by

Subhash Chintalapudi
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
4 views2 pages

Deep Learning Important Questions

The document outlines important questions for a semester-end examination on Deep Learning Techniques at JNTU Kakinada, covering five units. Each unit consists of three questions focusing on topics such as the fundamentals of deep learning, neural networks, CNN and RNN architectures, and applications in machine vision and natural language processing. The questions aim to assess students' understanding of key concepts, architectures, and tools in deep learning.

Uploaded by

Subhash Chintalapudi
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

Important Questions for Semester End

Examination
Course: Deep Learning Techniques
University: JNTU Kakinada
Pattern: Semester End Examination
Total Questions: 15 (3 per Unit)

UNIT I: Fundamentals of Deep Learning


1. 1. Explain the history and evolution of Machine Learning, highlighting the role of
probabilistic models and early neural networks.
2. 2. Discuss the differences between Decision Trees, Random Forests, and Gradient
Boosting Machines with suitable examples.
3. 3. What are the four branches of Machine Learning? Explain how overfitting and
underfitting affect model performance.

UNIT II: Introducing Deep Learning


4. 4. Compare and contrast biological vision systems with machine vision systems.
5. 5. Describe the architecture and training process of Artificial Neural Networks (ANNs).
6. 6. Explain the techniques used to improve deep network performance during training.

UNIT III: Neural Networks and Tools


7. 7. Illustrate the anatomy of a neural network with a labeled diagram and explain each
component.
8. 8. Write short notes on Keras, TensorFlow, Theano, and CNTK. How are they used in
deep learning?
9. 9. Describe the process of setting up a deep learning workstation and implementing
binary classification using neural networks.

UNIT IV: CNN and RNN Architectures


10. 10. Explain the concept of representation learning and the role of convolutional layers
in CNNs.
11. 11. Describe the architecture and working of Recurrent Neural Networks (RNNs) with
an example.
12. 12. How are CNNs implemented using PyTorch? Illustrate with a sample code or
architecture.
UNIT V: Applications and Research in Deep Learning
13. 13. Discuss the applications of deep learning in Machine Vision and Natural Language
Processing.
14. 14. Explain the architecture and use cases of Generative Adversarial Networks (GANs).
15. 15. Write short notes on Autoencoders, Restricted Boltzmann Machines (RBMs), and
Deep Belief Networks (DBNs).

You might also like