Scribd
Upload
131 views

Week 1 Assignment Questions

This document contains 10 questions about visual computing and machine vision. The questions cover commonly used tools like convolutional neural networks and PyTorch, the benefits of GPUs for parallel computing and faster convergence, market projections for machine vision, texture analysis methods like local binary patterns, factors that impact neural network parameters and classification functions.

Uploaded by

Guru75
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
131 views

Week 1 Assignment Questions

This document contains 10 questions about visual computing and machine vision. The questions cover commonly used tools like convolutional neural networks and PyTorch, the benefits of GPUs for parallel computing and faster convergence, market projections for machine vision, texture analysis methods like local binary patterns, factors that impact neural network parameters and classification functions.

Uploaded by

Guru75
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Deep Learning for Visual Computing

Week 1: Assignment Questions

Answer all Questions.


1. What are the commonly used tools for visual computing
(a) Machine learning
(b) Convolutional neural networks
(c) Pytorch
(d) Computer Vision
2. What is the major feature for employing GPUs in machine vision
(a) Faster convergence
(b) Parallel computing
(c) Less cost
(d) Better accuracy
3. What is the market for machine vision for 2020
(a) 3.5 Billion
(b) 9.5 Billion
(c) 6.5 Billion
(d) 6 Billion
4. Which of the following is a statistical texture metric
(a) Local Binary Patterns
(b) Fourier Coefficients
(c) Orientation Histogram
(d) Wavelets
5. The size of the Co-occurrence matrix depends on
(a) Gray levels in image
(b) Image contrast
(c) Image entropy
(d) None of these
6. Which of the factors govern high frequency attributes of Gabor wavelet?
(a) Centroid of receptive field
(b) Spatial frequency
(c) Standard deviation of Gaussian
(d) All of these

1
7. What is the output of sigmoid function for an input with dynamic range
[0, inf ]?

(a) [ 0, 1 ]
(b) [ -1, 1]
(c) [ 0.5, 1]
(d) [ 0.25, 1]
8. Assume a neural network with 100 input neurons, 50 hidden neurons and
2 output neurons. How many parameters are to be learned?

(a) 5100
(b) 5152
(c) 50
(d) 10000

9. Which of the following function is used for classification?

(a) Mean square error


(b) Absolute loss
(c) KL Divergence
(d) Negative log likelihood
10. What is the local binary pattern of
9 3 2
5 4 1
2 7 8
(a) 0 0 0 1 1 0 1 1
(b) 1 0 0 0 1 1 0 1
(c) 1 1 0 0 1 1 0 1
(d) 0 0 1 1 0 1 1 0

End

You might also like