## Sequence Models

Sequence models are the machine learning models that input or output sequences of data. Sequential data includes text streams, audio clips, video clips, time-series data and etc. Recurrent Neural Networks (RNNs) is a popular algorithm used in sequence models.

Applications of Sequence Models
1. Speech recognition: In speech recognition, an audio clip is given as an input and then the model has to generate its text transcript. Here both the input and output are sequences of data.

2. Sentiment Classification: In sentiment classification opinions expressed in a piece of text is categorized. Here the input is a sequence of words.

3. Video Activity Recognition: In video activity recognition, the model needs to identify the activity in a video clip. A video clip is a sequence of video frames, therefore in case of video activity recognition input is a sequence of data.

These examples show that there are different applications of sequence models. Sometimes both the input and output are sequences, in some either the input or the output is a sequence. Recurrent neural network (RNN) is a popular sequence model that has shown efficient performance for sequential data.

What is the difference between the actual output and generated output known as?

A. Output Modulus

B. Accuracy

C. Cost

D. Output Difference

Ans : Cost

Q.2 Prediction Accuracy of a Neural Network depends on _______________ and ______________.

A. Input and Output

B. Weight and Bias

C. Linear and Logistic Function

D. Activation and Threshold

Ans : Weight and Bias

Q.3 GPU stands for __________.

A. Graphics Processing Unit

C. General Processing Unit

D. Good Processing Unit

Ans : Graphics Processing Unit

Q.4 Recurrent Neural Networks are best suited for Text Processing.

A. True

B. False

Ans : True

Q.5 Recurrent Networks work best for Speech Recognition.

A. True

B. False

Ans : True

Q.6 Gradient at a given layer is the product of all gradients at the previous layers.

A. True

B. False

Ans : True

Q.7 Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.

A. True

B. False

Ans : True

Q.8 In a Neural Network, all the edges and nodes have the same Weight and Bias values.

A. True

B. False

Ans : False

Q.9 __________ is a Neural Nets way of classifying inputs.

A. Learning

B. Forward Propagation

C. Activation

D. Classification

Ans : Forward Propagation

Q.10 Name the component of a Neural Network where the true value of the input is not observed.

A. Hidden Layer

C. Activation Function

D. Output Layer

Ans : Hidden Layer

Q.11 ____________ works best for Image Data.

A. AutoEncoders

B. Single Layer Perceptrons

C. Convolution Networks

D. Random Forest

Ans : Convolution Networks

Q.12 _____________ is a recommended Model for Pattern Recognition in Unlabeled Data.

A. CNN

B. RNN

C. Autoencoders

D. Shallow Neural Networks

Ans : Autoencoders

Q.13 Process of improving the accuracy of a Neural Network is called _______________.

A. Forward Propagation

B. Cross Validation

C. Random Walk

D. Training

Ans : Training

Q.14 Data Collected from Survey results is an example of ____________.

A. Data

B. Information

C. Structured Data

D. Unstructured Data

Ans : Structured Data

Q.15 Support Vector Machines, Naive Bayes and Logistic Regression are used for solving ___________ problems.

A. Clustering

B. Classification

C. Regression

D. Time Series

Ans : Classification

Q.16 The rate at which cost changes with respect to weight or bias is called ____________.

A. Derivative

C. Rate of Change

D. Loss

Q.17 What does LSTM stand for?

A. Long Short Term Memory

B. Least Squares Term Memory

C. Least Square Time Mean

D. Long Short Threshold Memory

Ans : Long Short Term Memory

Q.18 A Shallow Neural Network has only one hidden layer between Input and Output layers.

A. True

B. False

Ans : True

Q.19 All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

A. True

B. False

Ans : False

Q.20 All the neurons in a convolution layer have different Weights and Biases.

A. True

B. False

Ans : False

Q.21 Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output.

A. True

B. False

Ans : True

Q.22 A Deep Belief Network is a stack of Restricted Boltzmann Machines.

A. True

B. False

Ans : True

Q.23 Restricted Boltzmann Machine expects the data to be labeled for Training.

A. True

B. False

Ans : False

Q.24 What is the method to overcome the Decay of Information through time in RNN known as?

A. Back Propagation

C. Activation

D. Gating

Ans : Gating

Q.25 What is the best Neural Network Model for Temporal Data?

A. Recurrent Neural Network

B. Convolution Neural Networks

C. Temporal Neural Networks

D. Multi Layer Perceptrons

Ans : Recurrent Neural Network

Q.26 RELU stands for ____________.

A. Rectified Linear Unit

B. Rectified Lagrangian Unit

C. Regressive Linear Unit

D. Regressive Lagrangian Unit

Ans : Rectified Linear Unit

Q.27 Why is the Pooling Layer used in a Convolution Neural Network?

A. They are of no use in CNN

B. Dimension Reduction

C. Image Sensing

D. Object Recognition

Ans : Dimension Reduction

Q.28 What are the two layers of a Restricted Boltzmann Machine called?

A. Input and Output Layers

B. Recurrent and Convolution Layers

C. Activation and Threshold Layers

D. Hidden and Visible Layers

Ans : Hidden and Visible Layers

Q.29 The measure of Difference between two probability distributions is know as ________________.

A. Probability Difference

B. Cost

C. KL Divergence

D. Error

Ans : KL Divergence