Scribd
Upload
58 views1 page

NNDL Mid - 2 Exam IMP Questions

The document contains important questions for a MID-2 exam on the NNDL subject, including multiple-choice questions, fill-in-the-blank items, and short and long answer questions. Topics covered include types of neural networks, limitations of deep learning, activation functions, and gradient descent methods. It serves as a study guide for students preparing for the exam.

Uploaded by

nareshamgoth04
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
58 views1 page

NNDL Mid - 2 Exam IMP Questions

The document contains important questions for a MID-2 exam on the NNDL subject, including multiple-choice questions, fill-in-the-blank items, and short and long answer questions. Topics covered include types of neural networks, limitations of deep learning, activation functions, and gradient descent methods. It serves as a study guide for students preparing for the exam.

Uploaded by

nareshamgoth04
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/ 1

Important Questions of MID-2 on NNDL subject

1.MCQ QUESTIONS:
 Which of the following is well suited for perceptual _____ neural networks tasks? [ ]
A) Recurrent B) Feed-forward C) Convolutional D) Reinforcement Learning
 Which of the following is/are Limitations of deep learning? [ ]
A) Data labeling B) Obtain huge training datasets C) Both A and B D) None of the above
 ____Number of connections from Input to Hidden, when Input 10 and the Hidden is 5. [ ]
A)less than 50 B) 50 C) more than 50 D) It is an arbitrary value
 Activation functions play an important role in many ANN's [ ]
A) Networking B) Neural Network C) Communication D) Both A & B
 CNN is mostly used when there is an? [ ]
A) unstructured data B) structured data C) Both A and B D) None of the above
 Which neural network has only one hidden layer between the input and output? [ ]
A) recurrent neural B) Deep neural C) Feed-forward neural D) Shalow neural
 A Multilayer Perception (MLP) is a_________ [ ]
A)Feed Back B) Single Layered C) Multi layered D) Feed forward
 Which of the following is a subset of machine learning? [ ]
A) Deep learning B) SciPy C) Numpy Learning D) All of the above
 The first layer is called the? [ ]
A) Outer Layer B) Inner Layer C) Hidden Layer D) None Of The Above
 RNNs stands for_________Networks? [ ]
A) Receives neural B) Report neural C) Recording neural D) Recurrent neural

Ii. Fill In The Blanks


 ANN Network uses layers of interconnected nodes , to work together to process and learn from________.
 Self Organizing Maps and Auto Connecters are __________ learning in Deep Learning
 Counter Propagation Network is basically constructed from_____________________ models.
 __________________ is the combination of both batch gradient descent and stochastic gradient descent.
 Stochastic gradient descent runs one training example per________________________.
 ___________________ algorithm that back propagates the errors from the output nodes to the input nodes..
 Batch gradient descent is used to find ________ for___________point in the training set and update the model
 In a fully connected Deep neural network, ________________layers connected one after the other
 Recurrent neural networks are yet another variation of ______________________networks.
 The cost function is defined as measurement of difference or error between ________________values.
Short Questions
 Define Deep Learning ?
 What are the Types of Deep Learning Networks?
 What is gradient based learning?
 What is Back Propagation ?
Long Questions
 What is Gradient Based Learning and Explain its types?
 Write about Back_Propagation Algorithm?
 Explain about Deep Feed-Forward Neural Network?
 Write are the Applications of Deep Learning and Its Advantages?

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy