Scribd
Upload
345 views5 pages

Deep Learning Techniques (Important Questions)

The document outlines important questions related to Deep Learning Techniques for an IV B. Tech (EEE) - I Semester course. It covers various units including AI concepts, deep learning architectures, neural networks, and machine vision, posing questions that encourage exploration of topics like optimization, CNNs, RNNs, and GANs. Each unit contains a series of questions designed to assess understanding and application of deep learning principles.

Uploaded by

krishnapranavi Bhallam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
345 views5 pages

Deep Learning Techniques (Important Questions)

The document outlines important questions related to Deep Learning Techniques for an IV B. Tech (EEE) - I Semester course. It covers various units including AI concepts, deep learning architectures, neural networks, and machine vision, posing questions that encourage exploration of topics like optimization, CNNs, RNNs, and GANs. Each unit contains a series of questions designed to assess understanding and application of deep learning principles.

Uploaded by

krishnapranavi Bhallam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Deep Learning Techniques

(IV B. Tech (EEE) – I Semester)


Open Elective - IV

Important Questions
Unit-1
1. Is AI a science or is it engineering? Or neither or both? Explain.
2. Write down the present and future scope of AI.
3. What is the Kernel Method in DL? Explain each.
4. Write down brief history & evolution of AI.
5. Define in your own words the terms: state, state space, search tree, search node.
6. Explain the terms Over fitting and Under fitting in ML
7. How random forests are related to Decision Trees?
8. What are the assumptions of Gradient Boosting Algorithm?
9. How can you improve the performance of the Gradient Boosting Algorithm?
10. What is Decision Tree Algorithm? Explain.
11. How is it possible to perform un-supervised learning with Random Forest?
12. Explain how random forests give output for classification and regression
problems.
13. Discuss Probabilistic modelling in detail.
14. Describe the role of Artificial Intelligence in Natural Language Processing.
15. How is it possible to perform un-supervised learning with Random Forests?
16. Interpret the concept of Underfitting with suitable example.
Deep Learning Techniques
(IV B. Tech (EEE) – I Semester)
Open Elective - IV

Unit-2

1. Explain about biological vision and machine vision.


2. Compare traditional machine learning approaches with current deep learning
approaches.
3. Explain the deep learning network architecture.
4. Explain the difference between AI, ML and DL.
5. Illustrate computation representation of language in Human and Machine
language.
6. Explain the Google duplex project.
7. Discuss the Softmax layer of a Fast Food – classifying Network.
8. Elaborate on various cost functions used in training deep networks.
9. What is optimization? What are the measures used to minimize cost?
10.Explain Adaptive gradient algorithm.
11.Explain the terms forward and backward propagation in ML.
12.How to know if our model is suffering from the Exploding/Vanishing gradient
problem.
13.How to improve Deep learning using weight initialization?
14.Enumerate the concept of L1 and L2 regularization in detail.
15.Discuss about types of Optimizers.
Deep Learning Techniques
(IV B. Tech (EEE) – I Semester)
Open Elective - IV

Unit-3

1. Explain the steps in setting up the deep learning workstation.


2. What is the best GPU for deep learning? Explain in detail.
3. Explain the terms loss function and optimizers with respect to DL.
4. Explain different types of neural networks.
5. Plot the graph between training (i.e no. of epochs) and validation loss. Explain.
6. Explain the anatomy of a neural network.
7. Discuss about keras workflow.
8. Explain about the architecture of Keras.
9. Explain the concept “Deep learning with Cloud”.
10.With a neat sketch, enumerate the concept of the deep-learning software and
hardware stack.
11.Explain the high-level building blocks required for developing deep-learning
models.
12.Inspect the implementation of binary classification.
13.Elaborate on Reuters dataset in detail.
14.Discuss the classification of newswires and explain with the dataset.
Deep Learning Techniques
(IV B. Tech (EEE) – I Semester)
Open Elective - IV

Unit-4
1. Explain about filters in CNNs.
2. Explain about BPTT algorithm.
3. Discuss neural networks and representation learning.
4. Explain the difference between ANN and CNN.
5. Explain the features of PyTorch library.
6. Explain the term recurrent units in RNNs.
7. Explain details of LSTM in RNN.
8. Explain why to use Recurrence neural networks other than CNNs.
9. Discuss PyTorch Vs TensorFlow.
10.Explain multi-channel convolutional operation in neural networks.
11.Explain convolutional operation in neural networks.
12.What do you mean by weight sharing? Explain weight sharing in CNNs.
13.What are the advantages of using convolutional neural networks over other neural
networks.
14.How CNNs and RNNs work with PyTorch.
15.Implement stride and padding with a practical example.
16.Enumerate the concept of sequence learning problems.
Deep Learning Techniques
(IV B. Tech (EEE) – I Semester)
Open Elective - IV

Unit-5
1. What is Deep-Net in Deep Learning.
2. How do Restricted Boltzmann machines work.
3. What are the advantages of Deep belief networks.
4. Discuss in detail about Denoising Auto encoders with a suitable example.
5. What are Boltzmann machines and Restricted Boltzmann machines?
6. Explain about Machine vision libraries.
7. What are the differences between GAN (generative adversarial networks) and
Auto-encoder?
8. What are the steps involved in a typical deep reinforcement learning algorithm.
9. Can you explain how an image sensor is in context with machine vision?
10.Explain Natural language Processing.
11.How do GANs work?
12.Explain various NLP (natural language processing) tools.
13.What are the regular algorithms used in NLP.
14.Discuss training the dataset in GANs.
15.What are some advantages of using machine vision over regular human
inspection?
16.Explain the types of GANs.

You might also like