Scribd
Upload
3 views1 page

Deep Learning and NLP Module Questions

The document contains a series of questions divided into two modules focusing on deep learning and natural language processing (NLP). Module 1 covers topics such as biological vision, deep learning architectures like LeNet-5 and AlexNet, and NLP concepts including word representation and Google Duplex. Module 2 addresses regularization techniques, dataset augmentation, meta algorithms, and optimization methods in deep learning.

Uploaded by

jeevan.m17112004
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
3 views1 page

Deep Learning and NLP Module Questions

The document contains a series of questions divided into two modules focusing on deep learning and natural language processing (NLP). Module 1 covers topics such as biological vision, deep learning architectures like LeNet-5 and AlexNet, and NLP concepts including word representation and Google Duplex. Module 2 addresses regularization techniques, dataset augmentation, meta algorithms, and optimization methods in deep learning.

Uploaded by

jeevan.m17112004
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

Module wise questions

Module 1

1. Define Deep Learning. Explain the history of biology vision.


2. Explain the experiment conducted by David Hubel & Wiesel at Hopkins University at late
90’s.
3. Write short on: biological vision, machine vision, traditional machine learning approach
& deep learning.
4. Explain LeNet–5.
5. Explain TensorFlow.
6 Explain brief ImageNet to ILSVRC along with AlexNet (Full Architecture).
1. Define NLP & explain industrial usage of it.
2. Explain one hot representation of words.
3. Word Vector (arithmetic derivation).
4. Word2Vec.
5. Localist vs Distributed Representation.
6. Google Duplex

Module – 2

1. What is regularization? Explain L2 parameter regularization with an example.


2. Explain L1 regularization. How does it differ from L2 regularization?
3. What is dataset augmentation? Give examples of common augmentation techniques.
4. What is noise robustness in machine learning models?
5. What is early stopping? How does it help in preventing overfitting?
6. Explain the three types of Meta Algorithms with examples.
7. What is parameter tying and sharing? Where is it applied in neural networks?
8. Explain sparse representation with suitable examples.
9. How does learning differ from pure optimization in machine learning?
10. Explain AdaGrad and write an algorithm of AdaGrad.
11. Differentiate between batch learning and mini-batch learning.
12. What are the major challenges in neural network optimization?
13. Discuss Stochastic gradient descent technique to reduce Loss function.
14. What are the basic optimization algorithms used in deep learning?
15. Write the RMSprop optimization algorithm and explain how it differs from AdaGrad in
handling the learning rate

You might also like