Scribd
Upload
98 views

ASC Assignment 1 and 2 Questions

The document contains short and long answer questions related to machine learning algorithms including linear regression, logistic regression, naive bayes classifier, neural networks, convolutional neural networks, and recurrent neural networks. The questions cover topics such as algorithm explanation, parameter tuning, overfitting, architecture details, and comparisons between different algorithms.

Uploaded by

shen shah
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
98 views

ASC Assignment 1 and 2 Questions

The document contains short and long answer questions related to machine learning algorithms including linear regression, logistic regression, naive bayes classifier, neural networks, convolutional neural networks, and recurrent neural networks. The questions cover topics such as algorithm explanation, parameter tuning, overfitting, architecture details, and comparisons between different algorithms.

Uploaded by

shen shah
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/ 2

CO-1 Assignment Questions

Short Answer Questions

1 Summarize breadth-first search algorithm with an example.

2 Summarize Depth-first search algorithm with an example.

3 Outline the gradient descent to reduce the cost function in linear regression.

4 Compare convex vs non-convex function.

5 Extend the gradient descent algorithm in logistic regression.

6 Compare linear regression and logistic regression.

Long Answer Questions

7 Outline bias and variance to fit degree 2 polynomial in linear regression.

8 Compare overfitting and underfitting.

9 Explain the Standardization of features in training a Logistic Regression.

10 Show the estimation of probabilities in naïve bayes classifier.

11 Explain various types of knowledge.

12 Explain the following uninformed search strategies with examples. a) Breadth-First Search. b) Depth First Search

13 Extend how overfitting is more likely when you have a huge amount of data to train?

14 Infer the best fit line for data in Linear Regression.

15 Explain knowledge based system.

16 Compare the pros and cons of naïve Bayes.

17 Explain the following uninformed search strategies with examples.

18 Explain different types of naïve bayes classifier.

19 Explain Linear Regression.

20 Show the cost function of linear regression.

21 Explain logistic regression.

22 Show the cost function of logistic regression.

23 Explain Bayes theorem to predict the probability.

24 Summarize the working of the naïve Bayes algorithm.

CO-2 Assignment Questions


Short Answer Questions

1 Illustrate Non-linear classification.

2 Explain the gradient descent algorithm.

3 Summarize the steps to train a neural network.

4 Demonstrate the concept of vanishing and exploding gradients.

5 Explain how the parameter sharing helps get rid of size limitations in RNN.

6 Compare the pros and cons of RNN.

Long Answer Questions

7 Illustrate the architecture of LSTM.

8 Show the derivatives of activation functions. Why do you need non-linear activation functions?

9 Explain the working process of convolutional neural networks.

10 Explain different types of RNN.

11 Explain the Edge detection mechanism in CNN.

12 Explain the core idea behind the LSTM with a neat diagram.

13 Infer some popular frameworks for deep learning.

14 Summarize the optimization algorithms in deep learning.

15 Explain max-pooling and down sampling in CNN.

16 Outline Bidirectional RNN.

17 Explain the convolution over RGB images.

18 Explain bias-variance trade-off in a deep learning neural networks.


19 Outline the importance of deep learning.

20 Compare the Biological and Artificial Neural network.

21 Explain Hopfield neural networks.

22 Extend the concept of recurrent neural networks.

23 Explain the basic components of CNN.

24 Explain the hyperparameters of the convolutional layer.

You might also like