Scribd
Upload
87 views

Assignment Questions

This document outlines questions for assignments on deep learning and image processing. For deep learning, it includes questions about perceptrons and backpropagation in neural networks, comparing ANN and CNN architectures, RNN types and backpropagation, GANs and other generative models, overfitting, Bayesian learning methods, and MAP and ML hypotheses. For image processing, it includes questions about image processing systems, digital image processing steps, high boost filtering, histogram equalization, restoration filters, color models and conversions, and compression coding standards. It is organized into units covering fundamental concepts in both deep learning and image processing.

Uploaded by

Jayaprakash B Achar
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
87 views

Assignment Questions

This document outlines questions for assignments on deep learning and image processing. For deep learning, it includes questions about perceptrons and backpropagation in neural networks, comparing ANN and CNN architectures, RNN types and backpropagation, GANs and other generative models, overfitting, Bayesian learning methods, and MAP and ML hypotheses. For image processing, it includes questions about image processing systems, digital image processing steps, high boost filtering, histogram equalization, restoration filters, color models and conversions, and compression coding standards. It is organized into units covering fundamental concepts in both deep learning and image processing.

Uploaded by

Jayaprakash B Achar
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

DEEP LEARNING

ASSIGNMENT QUESTIONS
1. i. Explain perceptron in an Artificial Neural Network and its different types. Unit -1
ii. Explain the application of perceptrons in real life. Unit -1
2. i. Explain backpropagation rule in neural networks. Unit-1
ii. Discuss Artificial Neural Network and its applications. Unit-1
3. Explain CNN architecture. Compare ANN and CNN. Unit-2
4. Explain CNN principles. Explain RNN and its different types. Unit-2
5. How backpropagation is different in RNN compared to ANN? Unit-3
6. What are the Trade-Offs Between GANs and other Generative Models? Unit-3
7. Explain Dynamic Programming and Monte-Carlo methods with examples. Unit-4
8. How to Avoid Overfitting in Deep Learning Neural Networks
9. Explain the features of Bayesian Learning Methods. Explain Bayes Theorem Unit-5
10. Explain MAP Hypothesis and ML Hypothesis with examples. Unit - 5

IMAGE PROCESSING

1. Explain the components of image processing system. Unit-1


2. Explain the fundamental steps in digital image processing. Unit-1
3. Discuss the characteristics of high boost filter for both frequency and spatial domain. Explain
how high boost filtering increases the enhancement of image with an example. Unit-2
4. For the given 4 x 4 image having grey scale between [0,9], get histogram equalized image and
draw the histogram of image before and after equalization. Unit-2
5.
2 3 3 2
4 2 4 3
3 2 3 5
2 4 2 4
Explain Deterministic-based and scholastic based restoration filters.
Discuss the drawbacks of Wiener fiter and how Kalman Filter overcome these drawbacks.
Unit -3
6. Explain RGB, CMY and HSL color models. Discuss procedure of converting RGB to HSL
colour model and vice versa. Unit -
3
7. Explain Huffman coding, Arithmetic coding, LZW coding, JPEG Compression standard.
Unit-4

8. Explain Morphological Image Processing and its different types. Unit-4

You might also like