H13-311_V3.0 Sample Questions Answers

country_code Country code representing the country where the passport was issued

nationality Nationality of representative holder

passport_number Representative passport number

confidence Confidence information of related fields. The greater the confidence, the higher the reliability of the corresponding field identified this time. In a statistical sense, the greater the confidence, the higher the

accuracy

Expectation reflects the average level of random variable values

The variance reflects the degree of deviation between the random variable and its mathematical expectation

Expectation and variance are both numerical characteristics of random variables

The greater the expectation the smaller the variance

__init__,Initialization parameters(Parameter), Submodule(Ce11),operator(Primitive)Equal group Software for initial verification

Construct, Define the execution process. In graph mode, it will be compiled into graphs for execution, and there is no syntax restriction

There's some left optim Commonly used optimizers,wrap Pre-defined commonly used network packaging functions Ce11

bprop (Optional), The reverse of the custom module

Building a calculation chart

Input tensor

Generate a session

Update weights I Right Answers)

Machines begin to understand, think and make decisions like humans

Machines begin to calculate and transmit information just like humans

The machine starts to understand and understand, make judgments, and take some simple actions

Convolutional layer

Pooling layer

Loop layer

Fully connected layer

Stand-alone mode

D1stnbuted mode

Reverse mode

Forward mode

Invented m 1989 by the Dutch Guido van Rossum, the first public release was issued in 1991.

Python 1s purely free software and the source code follows the GPL (GNU General Public License) protocol

Python syntax is simple and clean One of the features is to force blank characters to be used as statement 1ndentat1on [Right Answers)

Python 1s often nicknamed glue language which can easily connect various modules made 1n other languages

L1 Regularization can do feature selection

L1 with L2 Regularization can be used for feature selection

L2 Regularization can do feature selection

L1 with L2 Regularization cannot be used for feature selection

Deep learning is a branch of machine learning

Deep learning and machine learning are mutually inclusive

Deep learning and machine learning are both artificial intelligence but have no relationship to each other

None of the above

name (Logo)

shape (Dimensionality)

type (Type)

node (Node)

TensorFlow

Caffe

Torch

Theano

Scikit..Jeam

TRUE

FALSE

Simple

Free

High-level language

Rich library

True

False

TRUE

FALSE

DVPP

GPU

AI Calculation engine

Chip system control CPU

True

False

True

False

A rich library of machine learning algorithms.

machine learning program is intuitive and easy to use.

Distributed and scalable big data computing engine.

Support for the R language but does not support the Python language

Explanatory

Process oriented

Object-oriented

Dynamic data type

Random gradient descent

Adadelta

Adagrad

momentum

RMSProp

App integrated

Let the service actively find users

Quickly convert and migrate existing models

According to user needs, push services at the right time and at the right time

TRUE

FALSE

28*23

28*28

29*29

23*23

TRUE

FALSE

Quick source code

Diverse tool chain

Complete documentation

plentiful API

Pruning

Feature selection

Data cleaning

Decision tree generation

TRUE

FALSE

7×24

5×24

5×12

7×12

True

False

TRUE

FALSE

TRUE

FALSE

TRUE

FALSE

Traditional rule-based methods, in which the rules can be explicitly clarified manually

Traditional rule-based methods use explicit programming to solve problems

The mapping relationship of the model in machine learning is automatically learned

The mapping relationship of the model in the machine learning institute must be implicit

tf.nn

tf. layers

tf boost

tf.contrib

arithmetic operator

Reasoning operator

Logical operator

Comparison operator

int (integer type)

long (long integer type)

float (floating point type)

complex (complex number type)

Python has added there regular expression module since version 1.5.

re regular expression module gives the Python language all the regular expression functionality.

re regular expressions are powerful tools for working with strings.

re regular expressions can only process string data not numeric data

True

False

Flnancial product recommendation

Predictive maintenance

Telecom customer retention

Retailer grouping

Client

feed

placeholder

fetch

Weak artificial intelligence

Perceptual intelligence

Behavioral intelligence

Strong artificial intelligence

Features are interpretable in traditional machine learning, but weak in deep learning

Features are weak in traditional machine learning, but strong in deep learning

Features are weak in interpretability in traditional machine learning and deep learning

Features are interpretable in traditional machine learning and deep learning

Unsupervised algorithm only processes “features” and does not process ·tags·

Dimensionality reduction algorithm is not unsupervised learning

K-means algorithm and SVM algorithm belong lo unsupervised learning

None of the above

Automatic differentiation

Automatic tuning

Automatic coding

Automatic parallel

The number of rows 1s greater than the number of columns

The number of rows 1s equal lo the number of columns

The number of rows is less than the number of columns

The number of rows has no relationship with the number of columns.

TRUE

FALSE

True

False

The verification set can coincide with the test set.

The test set can coincide with the training set

The subset used to pick hyperparameters is called a validation set

Typically 80% of the training data 1s used for training and 20% 1s used for verification.

result

content

data

text

The difference between a list and a tuple is that the elements of the tuple cannot be

The list uses square brackets and the tuple uses parentheses

Tuple creation is very simple just add elements in parentheses and separate them wrth commas

When a tuple contains only one element you need to add a comma after the element