wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Edge Quiz

Total questions: 158

Worksheet time: 1hrs 23mins

Name
Class
Date
1.

What is Cloud Computing?

a)

It is a way to access software and services over the internet.

b)

It is a way to physically connect multiple computers together

c)

It is a way to protect data from unauthorized access.

d)

It is a way to store data on your local computer.

2.

Which of the following is NOT an advantage of Edge Computing?

a)

Low investment cost

b)

Significantly reduced data storage requirements

c)

Reduces Network Bandwidth Requirements

d)

Faster response time

3.

Based on the lecture, which of the following is not a typical deployment challenge for Edge computing devices?

a)

Power

b)

Waterproofing

c)

Thermal

d)

Sound proofing

4.

Which of the following is a good example of an AIoT application?

a)

A smart home thermostat that learns your preferences over time

b)

A fitness tracker that monitors your heart rate and sleep patterns

c)

A wearable device that tracks your steps and calories burned

d)

A wireless security camera that sends alerts to your smartphone

5.

What is the purpose of AIoT?

a)

To improve the design of IoT devices

b)

To integrate artificial intelligence with internet of things

c)

To replace IoT devices with AI-powered devices

d)

To create a secure network for IoT devices

6.

Match the Edge computing platforms to how they perform inferencing on the device.

a)

GPU-centric

b)

CPU-centric

c)

Raspberry Pi

d)

NVidia Jetson

7.

Match the Edge computing platforms to how they perform inferencing on the device.

a)

CPU-centric

b)

NVidia Jetson

c)

GPU-centric

d)

Raspberry Pi

8.

Which of the following is not a benefit of AIoT? (pick the best answer)

a)

Enhanced security

b)

Improved energy efficiency

c)

Increased productivity

d)

Decreased complexity

9.

AIoT stands for?

a)

Artificial Internet of Things

b)

Advanced IoT

c)

Artificial Intelligence of Things

d)

Artificial Intelligence on IoT

10.

Which of the following is a limitation of AIoT?

a)

It requires a high degree of technical expertise to implement

b)

It can be expensive to implement

c)

It is only suitable for large-scale applications

d)

It is limited by the processing power of IoT devices

11.

Which of the following is TRUE about Fog Computing?

a)

Fog provides low latency

b)

Fog computing are located nearer to the Cloud computing

c)

Fog computing is a separate architecture that can replace cloud computing.

d)

Cloud is a centralized system, while the fog is a distributed decentralized infrastructure

12.

In BLE terminology, what is a 'GATT'?

a)

Generic Audio Transmission Techno

b)

Generic Attribute Profile

c)

Generic Authentication Transfer Tool

d)

Generic Access Transmission Technique

13.

LoRa's spreading factor affects which of the following?

a)

Power consumption only

b)

Operating frequency

c)

Data rate and range

d)

Modulation technique

14.

Which standard does HaLow follow for wireless communication?

a)

802.11ah

b)

802.11b

c)

802.11ac

d)

802.11n

15.

Which Sub-GHz ISM frequency does LoRa operate in Singapore?2.4 Ghz

a)

2.4 Ghz

b)

868 Mhz

c)

466 Mhz

d)

923 Mhz

16.

Link Budget …

a)

refers to the amount of loss that a data link (transmitter to receiver) can tolerate in order to operate properly

b)

refers to the amount of loss that a data link (transmitter to receiver) should have.

c)

refers to the difference between the minimum expected power received at the receiver's end, and the receiver's sensitivity.

d)

refers to a connection between two entities

17.

In LoRa, which class does the following end device fall under: Battery-powered actuators, Energy efficient with latency controlled downlink, Slotted communication synchronized with a beacon.

a)

D

b)

B

c)

C

d)

A

18.

. Which of the following do not contribute to routing in a ZigBee network?

a)

ZigBee Router

b)

ZigBee End Device

c)

ZigBee Master

d)

ZigBee Coordinator

19.

Bluetooth is designed for short broadcasts. There are forty 2-Mhz channels. How many of these channels are reserved for advertising? (enter numerical number)

(a)  

20.

What is the maximum data rate of the latest BLE?

a)

1 Mbps

b)

3 Mbps

c)

2 Mbps

d)

4 Mbps

21.

What is the role of Zigbee end devices in the Zigbee network?

a)

Communicates with other nodes

b)

Controls the network

c)

Both

d)

None

22.

Z-Wave is an implementation of a ZigBee protocol.

a)

True

b)

False

23.

Which frequency does Z-Wave operate on?

a)

433 Mhz

b)

868 Mhz

c)

2.4 Ghz

d)

5 Ghz

24.

Which class of LoRaWAN is designed for bidirectional end-devices with scheduled receive slots?

a)

Class C

b)

Class D

c)

Class A

d)

Class B

25.

What is the purpose of Zigbee communication?

a)

Healthcare

b)

Industrial Control

c)

Home Automation

d)

All of the above

26.

In LoRa, what does increasing the spreading factor (SF) do to the signal's range and data rate?

a)

Increases range and decreases data rate

b)

Decreases both range and data rate

c)

Decreases range and increases data rate

d)

Increases range and data rate

27.

Which of the following is not a feature of Zigbee? (choose the best one)

a)

High Security

b)

Low Power Consumption

c)

Real-time Communication

d)

Large Bandwidth

28.

What is a characteristic of BLE's 'Advertising' mode?

a)

Secure data encryption.

b)

b. High data transfer rate.

c)

Device discovery and connection establishment.

d)

Long-range communication.

29.

What does 'Pairing' in BLE involve?

a)

What does 'Pairing' in BLE involve?

b)

Exchanging security keys for secure communication.

c)

Connecting two devices for data transfer.

d)

Adjusting the power level for optimal connection.

30.

What type of modulation is used in LoRa?

a)

Amplitude Modulation (AM)

b)

Chirp Spread Spectrum (CSS)

c)

Phase-Shift Keying (PSK)

d)

Frequency Shift Keying (FSK)

31.

What is the range typically achievable with BLE technology?

a)

Up to 50 meters

b)

Up to 150 meters

c)

Up to 100 meters

d)

Up to 10 meters

32.

LoRa modulation is a variation of ...

a)

Chord Spread Spectrum

b)

Chord Space Spectrum

c)

Chirp Spread Spectrum

d)

Chirp Spectrum Sector

33.

LoRa modulation technique sits at which OSI layer?

a)

Physical

b)

Transport

c)

Presentation

d)

Session

e)

Application

34.

Which of the following supports low energy radio operation?

a)

HaLow

b)

Bluetooth

c)

BLE

d)

WiFi

35.

Which Class of LoRaWAN is best suited for applications requiring minimal latency?

a)

Class B

b)

Class A

c)

Class D

d)

Class C

36.

What does LoRaWAN stand for?

a)

Long Range Wide Area Network

b)

Logical Routing WAN

c)

Low Range Wide Area Network

d)

Low Radiation Wireless Access Network

37.

What is the operating frequency of HaLow?

a)

5 Ghz

b)

900 Hz

c)

2.4 Ghz

d)

Sub-1 Ghz

38.

What is the main function of the Device EUI in LoRaWAN?

a)

To define the device's operating frequency

b)

To specify the data rate

c)

To encrypt data

d)

To identify the device uniquely on the network

39.

LoRaWAN's network server is responsible for:

a)

Processing and forwarding data to application servers

b)

Managing the radio frequency spectrum

c)

Controlling the power output of end devices

d)

Directly interacting with end-user applications

40.

Which network topology is not supported by ZigBee?

a)

Bus

b)

Star

c)

Cluster Tree

d)

Mesh

41.

Which of the following is needed to be a "ZigBee Compliant Product"

a)

ZigBee Stack

b)

IEEE 802.15.4

c)

IEEE 802.11

d)

Application Profile

42.

Zigbee have a transport layer.

a)

True

b)

False

43.

What is the main advantages of using LoRa for IoT applications?

a)

High Data Rate

b)

Low Data Rate

c)

Low Power Consumption

d)

Long Range

44.

In BLE, what is the role of a 'Central' device?

a)

It only receives data

b)

It connects to and controls peripheral devices.

c)

It acts as an intermediary between two devices.

d)

It broadcasts data to peripheral devices.

45.

Which of the following Topology does Bluetooth 4.0 support?

a)

Mesh

b)

Scatter Net

c)

Star

d)

Ring

46.

What does LoRa stand for?

a)

Long Resonance

b)

Low Range

c)

Long Radio

d)

Long Range

47.

What is the typical range of HaLow compared to traditional Wi-Fi?

a)

Same range

b)

Shorter range

c)

Longer range

d)

Unlimited range

48.

Which frequency band does BLE operate in?

a)

5.0 GHz

b)

2.4 GHz

c)

433 MHz

d)

868 MHz

e)

915 MHz

49.

LoRaWAN modulation technique sits at which OSI layer?

a)

Application

b)

Physical

c)

Network

d)

Session

e)

Datalink

50.

LoRa is primarily used for?

a)

Long-range, low-power consumption

b)

Short-range communication

c)

Audio and video transmission

d)

Faster speeds

51.

Which feature distinguishes BLE from Classic Bluetooth?

a)

Longer range

b)

Lower energy consumption.

c)

Higher data transfer rates.

d)

Better audio quality.

52.

BLE supports which kind of communication topology?

a)

Point-to-Point

b)

Star

c)

Bus

d)

Mesh

53.

Which of the following schemes is used by Bluetooth?

a)

Frequency hopping FDD scheme

b)

DSSS FDD scheme

c)

Frequency hopping TDD scheme

d)

DSSS TDD scheme

e)

Pyramid scheme

54.

What does BLE stand for?

a)

Basic Link Encryption

b)

Bluetooth Long Engagement

c)

Bluetooth Low Energy

d)

Bluetooth Low Efficiency

55.

What is the role of Zigbee routers in the Zigbee network?

a)

Acts as a relay between other nodes

b)

Controls the network

c)

Both

d)

None

56.

BLE is particularly designed for:

a)

Audio streaming

b)

Long-distance communication

c)

High-speed data transfer

d)

Short-range, low-power communication

57.

What is the main drawback of using LoRa for IoT applications?

a)

High power consumption

b)

Limited data rate

c)

Long range

d)

Short range

58.

What is the role of Zigbee coordinator in the Zigbee network?

a)

Controls the network

b)

Communicates with other nodes

c)

Both

d)

None

59.

What is the HTTP method used to create a new resource in RESTful architecture?

a)

PUT

b)

DELETE

c)

POST

d)

GET

60.

What is the default port number for MQTT?

a)

8080

b)

1833

c)

80

d)

8883

61.

What is a topic in MQTT?

a)

A string used to filter messages in a publish/subscribe model

b)

A unique identifier for a message

c)

A unique identifier for a message

d)

A message payload

62.

MQTT is _______ oriented.

a)

Data

b)

Device

c)

Message

d)

Network

63.

MQTT transmits data to and from a broker in which format. (Choose the best option)

a)

Text based data

b)

XML

c)

JSON

d)

Binary data

64.

What type of protocol is MQTT?

a)

Application protocol

b)

Network protocol

c)

Transport protocol

d)

Presentation protocol

65.

What is a resource in the context of RESTful web services?

a)

An entity that can be accessed and manipulated through a URI

b)

A function that performs a specific action

c)

A function that performs a specific action

d)

A set of procedures for accessing a database

66.

In RESTful APIs, what is used to uniquely identify a resource?

a)

API key

b)

URI (Uniform Resource Identifier)

c)

Session ID

d)

Query parameters

67.

In RESTful APIs, what does a status code in the 5xx range signify?

a)

Server error

b)

Redirection

c)

Successful operation

d)

Client error

68.

Which protocol is CoAP closely modeled after?

a)

HTTP

b)

AMQP

c)

FTP

d)

MQTT

69.

CoAP Protocol is comprised of which sub-layers?

a)

UDP

b)

Request & Response

c)

Observation

d)

Message

70.

What is the maximum number of clients that can subscribe to a single topic in MQTT?

a)

10

b)

1

c)

100

d)

Unlimited

71.

What does CoAP stand for?

a)

Compact Application Protocol

b)

Constrained Application Protocol

c)

Common Application Protocol

d)

Control Application Protocol

72.

What does MQTT stand for?

a)

Message Querying Telecommunication Transmission

b)

Message Queuing Transaction Transport

c)

Message Queuing Telemetry Transport

d)

Message Quorum Transport Technology

73.

Which layer is CoAP?

a)

Transport layer

b)

Application layer

c)

Service layer

d)

Control layer

74.

CoAP is specialized in?

a)

Wired applications

b)

Internet applications

c)

Wireless applications

d)

Device applications

75.

What transport layer protocol does CoAP use?

a)

ICMP

b)

REST

c)

UDP

d)

TCP

76.

CoAP supports which of the following methods similar to HTTP?

a)

CONNECT, TRACE, PATCH

b)

None of them

c)

OPTIONS, HEAD

d)

GET, POST, PUT, DELETE

77.

CoAP messages can be of which types?

a)

Confirmable and Non-Confirmable

b)

Request and Response

c)

Synchronous and Asynchronous

d)

Persistent and Transient

78.

CoAP is designed for which kind of networks?

a)

Resource-constrained networks

b)

Datacenter Networks

c)

Wide Area Networks (WAN)

d)

Local Area Networks (LAN)

79.

Which of the following is NOT a constraint of RESTful architecture?

a)

Cookie-based authentication

b)

Cacheability

c)

Statelessness

d)

Statelessness

80.

What does idempotence mean in the context of RESTful APIs?

a)

The API produces different results with each reques

b)

The API can handle asynchronous requests

c)

The API encrypts data for security

d)

The API produces the same result no matter how many times the same request is made

81.

The core of the protocol is specified in ______?

a)

RFC 7452

b)

RFC 7252

c)

RFC 7524

d)

RFC 7254

82.

To receive a retained message?

a)

You must keep the message.

b)

You must subscribe with the retained message set

c)

You must subscribe to a topic that has been published with the retained message set.

d)

You must subscribe with a QOS of 1 or 2

83.

Which HTTP status code indicates a successful GET request in a RESTful API?

a)

400 Bad Request

b)

201 Created

c)

200 OK

d)

500 Internal Server Error

84.

CoAP is a specialised _________ protocol.

a)

Power

b)

Web transfer

c)

Resource

d)

Application

85.

Which of the following QoS levels in MQTT ensures message delivery at least once?

a)

QoS 0

b)

None of them

c)

QoS 2

d)

QoS 1

86.

Which of the following is not a characteristic of MQTT?

a)

Quality of Service (QoS)

b)

Request/response messaging model

c)

Low overhead

d)

Publish/subscribe messaging model

87.

he Last Will Message is used to:

a)

Gain inheritance

b)

Notify a publisher of a network failure

c)

Guarantee that the message was delivered

d)

Notify clients of a failure in the publisher

88.

Which of the following is not a client type in MQTT?

a)

Broker

b)

Publisher

c)

Producer

d)

Subscriber

89.

In RESTful APIs, what is the purpose of a payload in a POST request?

a)

To provide additional headers

b)

To deliver the client's request to the server

c)

To contain the data being sent by the client

d)

To carry control information

90.

What is the primary role of a RESTful API's Uniform Interface constraint?

a)

To define specific operations like GET and POST

b)

To separate client and server implementations

c)

To ensure that the API is stateful

d)

To standardize the way clients interact with the server

91.

Which HTTP method should be used to update an existing resource in RESTful web services?

a)

PUT

b)

GET

c)

POST

d)

DELETE

92.

MQTT uses the publish/subscribe model. How does the publisher know who is subscribing?

a)

The subscriber informs the publisher

b)

Publisher uses the "Eye of Sauron"

c)

The publisher doesn't know

d)

The publisher gets notified when they subscribe.

93.

CoAP provides which of the following requirements?

a)

Simplicity and low overhead

b)

Lower overhead and multicast support

c)

Multicast support and simplicity

d)

Multicast support, lower overhead and simplicity

94.

What mechanism does RESTful APIs use to indicate the current state of the resource?

a)

HTTP headers

b)

Response body

c)

HTTP status codes

d)

API tokens

95.

Select the TRUE statement(s) for CoAP protocol?

a)

Uses GET message requests to retrieve subscription

b)

Uses FETCH message requests to retrieve subscription.

c)

Uses PUSH message requests to create subscription.

d)

Uses PUT message requests to create subscription.

96.

What does REST stand for?

a)

Real-time State Transfer

b)

Representational State Transfer

c)

Remote Server Transaction

d)

Relative State Transmission

97.

Which of the following HTTP methods is used to retrieve a resource in RESTful architecture?

a)

PUT

b)

GET

c)

POST

d)

DELETE

98.

What type of architecture does RESTful APIs follow?

a)

Peer-to-peer architecture

b)

Monolithic architecture

c)

Client-server architecture

d)

Publisher-Subscriber architecture

e)

Microservices architecture

99.

Which of the following is not a valid time domain feature?

a)

Root Mean Square Energy

b)

Zero Crossing Rate

c)

Spectral Centroid

d)

Amplitude Envelope

100.

What is the typical audio sampling rate?

a)

44.1 kHz

b)

20 kHz

c)

88 kHz

d)

22 kHz

101.

Which of the following is an important feature for speech recognition?

a)

All of the above

b)

Edges

c)

Histogram of gradients

d)

Spectral features

102.

Which type of input will be best suited as an input to a machine learning algorithm?

a)

Raw audio signal

b)

Spectrogram of audio signal

c)

Spectrum of audio signal

d)

Filtered audio signal

103.

What is the importance of Mel-scale?

a)

Sounds of equal distance on the Mel Scale are perceived to be of equal distance to humans

b)

It is easier for a machine learning algorithm to tackle

c)

It is easier for a machine learning algorithm to tackle

d)

It is a form of compression of audio signals

104.

Which of the following sound frequencies will a normal human able to distinguish better?

a)

10000 to 10200 Hz

b)

1000 to 1200 Hz

c)

5000 to 5200 Hz

d)

100 to 200 Hz

105.

What is the need of a power spectrogram?

a)

What is the need of a power spectrogram?

b)

None of the above

c)

To capture the change of frequency of a signal with time

d)

To capture the change of amplitude of a signal with time

106.

What is the typical fundamental frequency range of adult voice?

a)

31 to 19000 Hz

b)

Below 85 Hz

c)

85 to 155 Hz

d)

165 to 255 Hz

107.

What is Cepstrum?

a)

It is a tool to find anomalies in the signal

b)

All of the above

c)

It is a tool to find frequencies in the signal

d)

It is a tool for finding spectrum of a spectrum

108.

Why YAMNet is a suitable sound classification model for edge applications?

a)

It is a decision tree based approach

b)

It uses multiple sound features as input

c)

None of the above

d)

It is based on light weight MobileNet v1

109.

Speech signals can be considered as which of the following type?

a)

Stationary signals

b)

Non-stationary signals

c)

Random signals

d)

None of the above

110.

Why audio analytics on the edge is an important task?

a)

Sensitivity of the data is critical for many applications

b)

Redundancy of the data can be reduced (enable compression)

c)

ast action (e.g. audio scene classification)

d)

All of the above

111.

What does a spectrum of a signal provide?

a)

A measure of noise in the signal

b)

All of the above

c)

A measure of frequency components present in the signal

d)

A measure of amplitude of the signal

112.

Which filter type attenuates frequencies higher than the cutoff point?

a)

Low-Pass

b)

Notch

c)

High-Pass

d)

Band-Pass

113.

Why are Mel-frequency cepstral coefficients (MFCC) commonly employed in speech processing?

a)

All of the above

b)

It emphasize features of the audio signal that are important for human speech

c)

It reduces the redundancy in speech processing

d)

It is one of the most efficient representations of speech for employing as an input to machine learning

114.

What will be the total size of a HoG feature vector if a 9 bin approach based on 8x8 window which is normalized for 16x16 block?

a)

256 x 1

b)

36 x 1

c)

9 x 1

d)

8 x 1

115.

Given an extremely resource constrained edge device (e.g. Raspberry Pi Pico) which is the following can be employed for hand land mark detection?

a)

A convolutional neural network (CNN) model

b)

A fully connected neural network mode

c)

Image features + support vector machine (SVM)

d)

Any of the above

116.

In a gray scale image which is uint8 type, what will be the value corresponding to gray color?

a)

0

b)

255

c)

124

d)

None of the above

117.

What does image gradient infer?

a)

Low frequency in the image

b)

Smooth texture in the image

c)

Colors in the image

d)

All sudden transitions (edges) in the image

118.

From the matrix size below, identify a color image

a)

256 x 256 x 3

b)

256 x 256

c)

256 x 256 x 2

d)

256 x 245 x 5

119.

Which of the following is useful for extracting depth from a video?

a)

Local binary descriptor

b)

Edges

c)

Optical flow estimations

d)

All of the above

120.

Which of the following is the definition of histogram of an image?

a)

A measure of frequency of occurrence of image intensities

b)

A measure of frequency of occurrence of edges in the image

c)

A measure of noise in the image

d)

All of the above

121.

Select a suitable window size for obtaining large image gradients in the image of size 256 x 256

a)

3 x 3

b)

8 x 8

c)

64 x 64

d)

256 x 256

122.

Which is supposed to be a high frequency component in an image?

a)

Random noise

b)

Edges in image

c)

Both a and b

d)

None of the above

123.

What is the preferred algorithm for hand gesture based interface?

a)

Direct hand landmark detection – gesture control

b)

Hand detection – Hand landmark detection – gesture control

c)

Direct gesture control

d)

None of the above

124.

What is the starting point of any edge detection?

a)

Smoothing followed by gradient operation

b)

Gradient operation alone

c)

Gradient followed by smoothing operation

d)

All of the above

125.

Which of the following feature(s) can be used for face detection in the image on an edge device?

a)

Histogram of oriented gradients

b)

Histogram of gradients

c)

Histogram of oriented textures

d)

None of the above

126.

Which of the following images has the highest resolution?

a)

256 x 256

b)

2048 x 2048

c)

1024 x 1024

d)

16 x 16

127.

Which is preferable edge only image analytics?

a)

Image segmentation

b)

Fingerprint informatics

c)

Object detection

d)

All of the above

128.

Which is the following is a reason for increased popularity for computer vision on the edge?

a)

Low latency is critical for fast action (e.g. motion segmentation)

b)

Sensitivity of the data is critical for many applications

c)

Redundancy of the data can be reduced (video summarization)

d)

All of the above

129.

Which of the following condition is apt for Pruning?

a)

The histogram of the weights centered around zeros

b)

A bi-modal Gaussian distributed histogram

c)

A Poisson distributed histogram

d)

None of the above

130.

Which of the following is a representation of linear symmetric quantization? (x is input, x_int is output, s is scale, z is zero point, b is number of bits

a)

x_int = clamp(round(x/s) + z , 0, 2^b – 1)

b)

x_int = clamp(round(x/s) + z , -2^b -1, 2^b – 1)

c)

x_int = clamp(round(x/s) , 0, 2^b – 1)

d)

None of the above

131.

What is a neural network distillation?

a)

The learned teacher model is Pruned to form a student model

b)

The learned teacher model is Quantized to form a student model

c)

Learning a student model with low complexity from a teacher model

d)

None of the above

132.

Pruning of neural networks can be done in which of the following ways

a)

Removing some of the weights

b)

Reducing the bit-resolution of the weights

c)

Reducing the spatial resolution of the input

d)

All the possibilities

133.

Which of the following cases is not useful for pruning of neural networks?

a)

A very deep neural network

b)

Pruning works in all cases

c)

A recursive neural network

d)

A modular network with the output of one neural network is input to the next

134.

How to make rounding error smaller?

a)

Decrease q_max

b)

Increase q_max

c)

Decrease q_min

d)

All of the above

135.

How do we find the scale factor and zero point of inputs/activations?

a)

Not possible

b)

Run representative mini-batches

c)

Derive from theory

d)

Predict from the trained model

136.

What will be the scale factor for a data with minimum value of -50 and maximum value of 150 and for 8-bit resolution.

a)

200

b)

0.7843

c)

0.0039

d)

None of the above

137.

What will be the dequantization function for a non-linear quantization (e.g. weight sharing)

a)

x' = s (x_int – z)

b)

x' = s*x_int

c)

Needs a look up table (or code book)

d)

Not available

138.

What will be the starting point for weight sharing by combining Pruning with Quantization?

a)

k-Means based clustering of weights

b)

Huffman Coding of Weights

c)

Quantization of Weights

d)

Pruning of Weights

139.

What will be the typical shape of a histogram after Pruning process?

a)

A Poisson distributed histogram

b)

A normal distributed histogram

c)

A bi-modal Gaussian distributed histogram

d)

Any of the above

140.

Which of the following has the highest complexity of implementation?

a)

Symmetric Signed Quantization

b)

Symmetric Unsigned Quantization

c)

Asymmetric Unsigned Quantization

d)

All the above are equal in complexity

141.

What will be the effective bit size for a quantization with level set {-1, 0, 1}?

a)

3 bits

b)

1.58 bits

c)

1 bit

d)

2 bits

142.

Which of the following is useful for implementing a deep neural network on the edge device?

a)

Higher number of parameters

b)

Neural network weights represented by 32 bit fixed point representation

c)

None of the answers

d)

Both the higher parameters and 32 bit fixed point representation

143.

Which of the below cases provides the best results?

a)

L2 regularization without retrain

b)

L1 regularization without retrain

c)

L1 regularization with retrain

d)

L2 regularization with iterative retraining

144.

There are a plenty of benchmark datasets for deep learning which are targeted at edge devices

a)

True

b)

False

145.

The aggregation of dataset and models in an Edge AI environment is known as Edge (a)  

146.

Which of the following languages/software is preferred for implementing on an edge device?

a)

Python

b)

Any of the following

c)

C or C++

d)

Matlab

147.

Which of the following software development kit is dedicated to STM32 microcontrollers?

a)

Nvidia TensorRT

b)

AMD DNNDK

c)

None of the following

d)

X-Cube AI

148.

Which of the following is a software tool for edge DL inference?

a)

ExecuTorch

b)

All of them

c)

Tensorflowlite

d)

Onnx

149.

Which of the following conditions is not important for an Edge AI deployment?

a)

Simultaneous design of algorithms with hardware

b)

All of the following

c)

The environmental conditions of edge AI deployment doesn’t really matter

d)

Tools for automatic mapping of trained models

150.

What is Edge Fleet Management?

a)

None of the following

b)

It is a hub where all the edge devices will publish/subscribe the data

c)

It is a network of edge devices

d)

It is a process of compressing DL algorithms to be run on an Edge Device

151.

Which software tool supports the Raspberry Pi for edge inference?

a)

Embedded Learning Library (ELL)

b)

Intel OpenVINO Toolkit

c)

None of the following

d)

Matlab Deep Learning HDL Toolbox

152.

The process of identifying the memory requirements and latency for running an ML algorithm on a specific hardware is known as?

(a)  

153.

It is not feasible to implement an unsupervised ML algorithm like k-Nearest Neighborhood (k-NN) on an edge device.

a)

True

b)

False

154.

What is the trimmed version of Python 3.x which could be run on an edge device?

(a)  

155.

It is possible to run an ML algorithm on a field programmable gate device (FPGA) or an application specific integrated circuit (ASIC)

a)

True

b)

False

156.

There are plenty of software frameworks available for neural architecture searches for edge devices.

a)

True

b)

False

157.

In Hierarchical Federated Learning, which of the following is correct?

a)

The model is trained at the edge

b)

The model is trained in the cloud

c)

The model is trained in the cloud and at the edge

d)

None of the above

158.

When the dataset is not shared, but the model is locally trained and shared across multiple compute devices, the framework is known as

a)

Localized Learning

b)

Federated Learning

c)

Globalized Learning

d)

Edge Learning