Scribd
Upload
81 views1 page

Deep Learning-Chorale Prelude

This document contains 31 true/false statements about various machine learning and deep learning concepts including neural networks, recurrent networks, convolutional networks, autoencoders, restricted boltzmann machines, and more. It covers topics like the components and functions of different neural network architectures, what types of problems and data they are best suited for, optimization techniques like training and backpropagation, common layers and units, and definitions of related terms.

Uploaded by

Jacob Thomas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
81 views1 page

Deep Learning-Chorale Prelude

This document contains 31 true/false statements about various machine learning and deep learning concepts including neural networks, recurrent networks, convolutional networks, autoencoders, restricted boltzmann machines, and more. It covers topics like the components and functions of different neural network architectures, what types of problems and data they are best suited for, optimization techniques like training and backpropagation, common layers and units, and definitions of related terms.

Uploaded by

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

1.

A Shallow Neural Network has only one hidden layer between Input and Output
layers.--true
2.What is the difference between the actual output and generated output known as?--
cost
3.Data Collected from Survey results is an example of ___________________.--
structured data
4.Name the component of a Neural Network where the true value of the input is not
observed.--hidden layer
5.Recurrent Networks work best for Speech Recognition.--true
6._______________ is a recommended Model for Pattern Recognition in Unlabeled
Data.--autoencoders
7.Support Vector Machines, Naive Bayes and Logistic Regression are used for solving
___________________ problems.--classification
8.________________ works best for Image Data.--convoulution networks
9.Process of improving the accuracy of a Neural Network is called
_______________.--training
10._____________________ is a Neural Nets way of classifying inputs.--forward
propogation
11.In a Neural Network, all the edges and nodes have the same Weight and Bias
values.--false
12.GPU stands for __________.--graphics processing unit
13.The rate at which cost changes with respect to weight or bias is called
__________________.--gradient
14.Neural Networks Algorithms are inspired from the structure and functioning of
the Human Biological Neuron.--true

15.What does LSTM stand for?--Long short team memory


16.What is the best Neural Network Model for Temporal Data?--recurrent neural
network
17.Why is the Pooling Layer used in a Convolution Neural Network?--dimension
reduction
18.What are the two layers of a Restricted Boltzmann Machine called?--recurrent and
convolution layers
19.Restricted Boltzmann Machine expects the data to be labeled for Training.--false
20.The measure of Difference between two probability distributions is know as
________________________.--KL divergence
21.What is the method to overcome the Decay of Information through time in RNN
known as?--gating
22.RELU stands for ______________________________.--rectified linear unit
23.All the Visible Layers in a Restricted Boltzmannn Machine are connected to each
other.--false
24.A Deep Belief Network is a stack of Restricted Boltzmann Machines.--true
25.A _________________ matches or surpasses the output of an individual neuron to a
visual stimuli.--convolution
26.Recurrent Network can input Sequence of Data Points and Produce a Sequence of
Output.--true
27.All the neurons in a convolution layer have different Weights and Biases.--false
28.Restricted Boltzmann Machine expects the data to be labeled for Training.--
false
29.Recurrent Neural Networks are best suited for Text Processing.--true
30.Autoencoders are trained using _____________________.--backpropogation
31.De-noising and Contractive are examples of __________________.--convolution
neural networks

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