CY305 TEE Prep

Patents give the owner the right to control...

...the manufacture, sale, import, and use of an invention.

Trademarks give the owner the right to control...

...the use of a mark in association with a good or service.

Trade Secrets give the owner the right to control...

...the use of the IP so long as individuals sign an NDA

Copyrights give the owner the right to control...

..reproduction,sale, derivatives, or performance of a work.

In linear classification, the decision boundary is the line created when f(x)=

0

In linear classification, the decision boundary is the line created when f(x)= ____?

0

With the logistic regression algorithm, the decision boundary is the line defined when f(x) = ____ ?

0

You create a logistic regression that predicts if a person will pass or fail the IOCT. When f(x) is positive the model predicts the person will pass. If f(x) = 0.5 what is the probability the person fails the IOCT? (Give your answer as a decimal number rounded to the nearest hundredths) Use 1/(1+e^f(x))

0.38

Given a model with 21 items classified as + and 79 classified as -, calculate the entropy.

0.741

A decision tree with two levels has an initial entropy of 0.94. After branching, the average entropy of the new level is 0.07. Calculate the total information gain, given below: IG=Hparent−Hchildren (Enter your answer as a decimal number rounded to the nearest hundredths.)

0.87

Given a binary classification model (i=2), with 22 items classified positively (+), and 18 items classified negatively (-), calculate the Entropy using the following equation: H=−∑ipilog2pi (Enter your answer as a decimal number rounded to the nearest hundredths.)

0.99

To log in, you type your username, password, PIN, and answer a security question. How many factors of authentication?

1

Match the database table components to the most appropriate definition. Column Row

1) Attribute 2) Record

What do the letters in the CIA triad stand for? A stands for C stands for I stands for

1) Availability 2) Confidentiality 3) Integrity

Match the network devices on the left with the layer they are most accurately associated with on the right. Switch Router Server

1) Data Link Layer 2) Network Layer 3) Application Layer

Match the terms with their definitions big data data mining supervised learning data cleansing

1) Data sets that are too large for traditional processing systems such as Microsoft Access 2) Automated extraction of useful (non-obvious) knowledge from data 3) Building a model using historic information where the outcome is known 4) Removing or amending data that is incorrect, incomplete, improperly formatted, or duplicated

Select the types of Joins

1) Inner Join 2) Right Outer Join 3) Left Outer Join

Select the types of relationships

1) One-to-Many 2) One-to-One 3) Many-to-Many

Assign each layer of the TCP/IP architecture a number from 1-5 representing its position in the network stack. Give the highest layer a 5 and the lowest layer a 1.

1) Physical 2) Data link 3) Network 4) Transport 5) Application

Match the neural network architecture with the types of problems it is typically used on. 1) Convolutional neural network 2) Recurrent neural network 3) Generative adversarial network

1) Spatial Relationship 2) Temporal Relationship 3) Creating new items similar to the originals

1) Regression 2) Clustering

1) Supervised 2) Unsupervised

Match the following terms to the definition which most appropriately pertains to them: 1) Data Driven Decision Making 2) Leakage 3) Clustering 4) Linear Regression

1) The practice of basing decisions on the analysis of data rather than purely on intuition. 2) Information in data that wasn't originally available at the moment of decision. 3) Grouping individuals in a population together by their similarity, without knowing beforehand what features are interesting. 4) Estimating/predicting the numerical value of some variable.

Match the chart type with its best practice use. 1) Bar chart 2) Line chart 3) Slopegraph 4) Scatter plot

1) Used to compare proportions between two or more categories 2) Used to show continuous change over time 3) Ideal for direct comparison of the rate of change between two states (such as before and after). 4) Used for identifying trends and patterns

Match the Following: 1) Decision Tree 2) Linear classifier

1) can partition on a single attribute 2) uses weighted combination of all attributes

Match the correct term from the right to the concept on the left. Trade secrets allow the holder to: Trade secret duration lasts:

1) keep information proprietary so long as it is kept secret. 2) until someone fails to protect it, or the product is reverse engineered.

Match the correct term from the right to the concept on the left. Copyright allows the holder to: Copyright duration lasts:

1) reproduce, distribute, display, perform, or create derivatives works. 2) 70 years after the death of the longest living author.

How many classes can a linear classification model predict?

2

To sign a DA form, you insert your CAC and type in your PIN. How many factors of authentication is this?

2

9-fold cross validation splits the data into ___ subsets?

9

A formula in Excel begins with what character?

=

Which of the following does NOT describe a computer network?

A computer's web browser opening a website that the user has saved to the local hard drive.

The term 'packet' refers to:

A formatted block of data transmitted across a network.

Which of the following describe the term 'layer' when used in the context of computer networks? Select all that apply.

A level of abstraction that hides the implementation details of other layers. A specific subset of protocols and specifications that describe how data is transmitted or routed through a network or transmission medium.

Which of the following does NOT describe a database table?

A method to 'ask a question' of the database.

Which answer best describes the Internet?

A network of interconnected networks

You begin selling your own brand of pencils called Never-Dull. You can protect the brand name of these pencils with:

A trademark

Which of the following makes for the best primary key when storing records of Soldiers in a table?

A unique number assigned to the Soldier when joining the Army

Thanks to which concept, you do not need to know or care where the webpage server you are trying access is physically located in the world.

Abstraction

With a One-to-Many relationship, what best describes how the relationship is formed between the two tables?

Add the primary key from the table on the One side to the table on the Many side as a foreign key.

Given the following normalized linear model, f(x)=93+3Attribute1−8Attribute2+6Attribute3, which is the most important attribute?

Attribute2

Which of the following is a security service provided by the Information Assurance model?

Availability

The data mining process includes which steps?

Business Understanding, Modeling, Data Understanding

Which category of data mining task attempts to predict a labeled or known categorical value?

Classification

Which of these is a machine learning task?

Classification

Choose two potential uses for SharePoint

Collaborate on documents, Build a website

Which security service ensures that only the INTENDED RECIPIENT can read your message?

Confidentiality

What are the three categories of the information security model?

Confidentiality,Integrity, & Availability

These are totals functions:

Count, Max, Sum

Which of the options below create a table in Excel?

Ctrl + T , Format as Table button

802.11 WiFi and Bluetooth are two protocols that reside at which layer?

Data Link Layer

Which stage of the data mining process often takes most of a data analysts' time?

Data preparation or formatting

What type of query attribute is created by combining other attributes using concatenation and/or mathematical operators such as addition or subtraction?

Derived attribute

Assume there is a one-to-many relationship from a Cadet to a Pass table. What prevents a user from relating a pass to a non-existent cadet when adding records to the Pass table?

Establishing referential integrity between these two tables when creating the relationship.

What is data mining?

Extracting useful, non-obvious knowledge from data

A functioning network requires access to the internet.

False

AND statements return results that meet any criteria

False

Cross Validation splits the data into training and testing set a single time

False

GROUP BY, AVERAGE, and COUNT are the only Totals functions available.

False

Information gain is a measure of impurity in the system.

False

Passwords should contain easily guessable parts.

False

Table column names cannot be used as references in Excel functions.

False

The logistic function is the only option for linear classifiers.

False

When the predicted class is positive and the actual class is negative the instance is a:

False Positive

Which media has the longest range and fastest speed?

Fiber Optic Cable

Which transmission media typically has the longest range and highest bandwidth but is generally more expensive and difficult to work with?

Fiber optic cable

A _____ value corresponds to the _______ in another table.

Foreign Key, Primary Key

An attribute in Table A that links one or more records in Table A to a single record in Table B is the:

Foreign key

Which of the following is a true statement about HTTPS?

HTTPS should be used for all secure web traffic

What feature is the distinguishing element of deep learning? (Choose the best answer)

Hierarchical feature learning

Pick the answer that most accurately describes public key cryptography.

Hosts generate private and public key pairs. Private keys are kept secret while public keys are published for anyone to use. These keys are mathematically related in such a way that only the private key can decrypt ciphertext encrypted with the public key, and vice versa.

What is the default join type that only includes records that are included in both tables?

Inner Join

Hashing algorithms can be used to provide which security service?

Integrity

Alice wants to send a message to Bob over the Internet. She first digitally signs the message (hashes the contents and then encrypts the resultant hash with her private key) and then encrypts the contents of the message with Bob's public key. Which security services are implemented with these actions?

Integrity, Non-repudiation, and Confidentiality

What is a learning curve used for?

It shows accuracy as a function of training data.

What is the biggest problem with using accuracy as an evaluation metric?

It treats all errors the same.

What is a major disadvantage of symmetric (private-key) encryption?

Key Exchange

SharePoint includes:

Lists, Pages, Document Libraries

Using the following password requirements guarantees an acceptable level of entropy.

Lower case, Numbers, Upper Case, Special Characters

Which type of address has the following properties: It uniquely identifies a network card It was assigned to the network card at the time of manufacture It is referred to as a physical address It is used by a switch to forward frames

MAC Address

If a database models Cadets and Courses, what is an appropriate relationship between them?

Many-to-Many

You are a school administrator and are creating a database to keep track of students and their academic schedules. You have determined that you must model the entities Student and Course in different tables. What is an appropriate relationship between these tables?

Many-to-Many between Student and Course

These are stages in the data mining process:

Modeling, Business Understanding, Data Preparation

Thanks to which concept, your computer can connect to the network using fiber, ethernet, and wireless?

Modularity

You want to connect multiple small networks together using a switch. What problem may occur if you do not have a Dynamic Host Configuration Protocol (DHCP) server for the combined network?

Multiple users could be assigned the same IP address.

A messaged signed with a digital signature is an example of:

Non-Repudiation

You are creating a database for managing the CY305 computer lab. There are many sections using the computer lab so the course director assigns each cadet a computer to use at the beginning of the semester. You have determined you must model the entities Cadet and Lab Computer as separate tables. What is the relationship between Cadet and Lab Computer?

One-to-Many relationship between Lab Computer and Cadet

Your database has a Cadet table with a one-to-many relationship to an APFT table. Each table is populated with data. You write a query that executes an inner join between Cadet and APFT (and no other criteria applied). What records from the Cadet table would you expect as a result?

Only cadets with an APFT result recorded in the APFT table.

Wireless networks face which of the following challenges? Select all that apply

Other networks using the same channel may cause interference. The strength of a wireless signal rapidly decreases as a user moves away from a wireless access point. Multiple users sharing the same wireless access point must share bandwidth.

To summarize an Excel table, you might use a:

Pivot Table

The Cybersecurity Process features which of the following?

Prevent, Respond, Detect

________ is the output of the logistic function.

Probability

The data science team creates a model and tells you it is 92% accurate. They determined accuracy by testing the model against the same 50 examples used to build the model. How would you expect the model to perform against a new dataset?

Probably less than 92% accuracy.

Categorize the pros and cons of VPNs

Pros- Traffic encrypted between you and the VPN server Obscures your IP address Can be used to access internal network resources Cons- Costs money and time VPN provider might collect data/logs Does not protect from cookies No Category- Makes your laptop really slow Can speed your laptop up The government is spying on me with VPNs

What is the foundation of all secure messaging on the open internet?

Public key cryptography

Which approach uses two different keys that are mathematically linked to encrypt and decrypt?

Public-key Cryptography

The operation in a relational database allowing the user to retrieve desired data from one or more tables, queries, or expressions is called a(n):

Query

Which of the following describe problems that are prevalent in wireless networking?

Radios transmitting in the same frequency band interfere

What is the minimum level of permission needed to view a SharePoint site?

Read

A ______ defines an ____ relationship

Relationship table, Many-to-Many

A network of computers needs to be connected to a seperate network. Which of the following network devices should be used to connect these networks?

Router

Which of the following are primarily layer 5 devices?

Server, Desktop Computer

Which of the below are valid data types in SharePoint?

Single Line Text, Currency

One of the three factors to authenticate a user:

Something you are

Which factor of authentication does biometrics use?

Something you are

In Access Control, the first step is to Authenticate a user to a system. This authentication can be done based on multiple factors. Which of the following is NOT a factor for authentication?

Something you did

Which of the following would be the best choice to connect 15 computers that are located within a single classroom? (They do not need to connect to anywhere else - only to each other.)

Switch

What kind of encryption uses the same key to encrypt and decrypt?

Symmetric

Which best describes why you might use the Transmission Control Protocol (TCP) rather than the User Datagram Protocol (UDP) download a PDF document from a website?

TCP will ensure that you correctly receive every packet transmitted by the server.

What value(s) do you adjust to build a ROC Curve?

The decision threshold or confidence at which the model makes a positive prediction

Which of the following elements IS NOT a qualifying element of a utility patent?

The invention must be fixed in a tangible medium.

What is expected value?

The sum of the probability of each outcome times the value of the outcome.

Which of the following is the best reason for using lookup fields in a form?

To control the input from the users

A SharePoint list can have multiple different views.

True

A query uses criteria to limit the results of the query.

True

A single query can contain multiple AND or OR statements.

True

Base Accuracy rate is the classification accuracy if you assume every instance belongs to the majority class

True

Data cleaning will most likely take a large amount of time.

True

Entropy is a measure of purity of a data set.

True

Expected Value of a model requires knowledge of cost and benefit of each prediction

True

One can use multiple attributes to define a single key.

True

PivotTables require you to use a summarization function in the Values area.

True

Support Vector Machine and Logistic Regression are linear classifiers

True

Tables automatically resize when you enter data adjacent to the table.

True

The decision boundary is the line created when f(x) = 0.

True

Using a GROUP BY statement for an attribute clusters all of the records with the same value for that attribute.

True

When the predicted class is negative and the actual class is negative the instance is a:

True Negative

A ROC Curve compares what two values for a given model?

True Positive Rate to False Positive Rate

______ : some conditions are too complex to use in one query. If true, the solution to this problem is ___________. If false, select N/A for option 2.

True, Intermediate Queries

Logging in to your machine to check e-mail with your CAC and pin is an example of:

Two-factor authentication

Which two protocols reside at the Transport Layer?

UDP and TCP

If you need to create a single chart graphing entirely different things what should you NOT do?

Use two separate y-axis on the same chart.

What would happen if a network did not have a DHCP server?

Users would have to set their own IP address

Which of the following best describes what would happen if West Point did not have internal servers registered on a Domain Name Service (DNS) server?

Users would need to enter an IP address (e.g., 134.240.2.10) rather than a URL (e.g., http://cy305sharepoint) to access an internally hosted website.

Choose the best description of phishing.

Using fraudulent emails, purporting to be from reputable sources, in order to induce individuals to reveal personal information, such as passwords and credit card numbers.

What mechanism allows for checking a user's input against a pre-defined set of rules?

Validation

Which of the following are factors of authentication?

What you are, What you have, What you know

What would happen if a network did not have a DNS server?

You have to type IP addresses instead of URLs websites

Which answer best describes a scenario where the user or organization would most likely NOT benefit from the time investment to build and maintain a database?

Your business manager wants to see a pie chart comparing each quarter of last year's returns.

A database is best described as...

a collection of related data from which users can efficiently retrieve desired information.

In artificial neural networks, the _________ describes the output of an artificial neuron.

activation function

A full outer join returns _________

all rows from both tables

Once the data type of a column in a list is set, it _________

can be changed under settings

An example of an analog database is a(n)

card catalog

A ____ is the intersection of a row and column.

cell

Information gain measures the _________.

change in entropy

Information gain measures the change in entropy from parent to

child

A WYSIWYG (What You See Is What You Get) web page editor, like the one used to create/modify a SharePoint webpage, _______ what the end result will look like while the page is being edited.

displays

Preventing data going into a foreign key field that is not in the related table is known as...

enforcing referential integrity

Decision trees partition on one __________ at a time.

feature

A primary key is a...

field in a table that uniquely identifies each record

A _________ shows accuracy as a function of complexity.

fitting graph

Excel Tables are useful because:

formulas propagate throughout a column there is a built-in totals row for math functions you can refer to columns by name

Choose the answer that best completes the following statement: Cross validation is a method to __________.

get a more accurate assessment of general model performance

Entropy (in Information Theory) is a measure of ___________.

impurity

Including the hash of the message provides:

integrity

An advantage of k-fold cross validation over simple hold out testing is that ____________.

k-fold cross validation trains the model on different subsets of data with each fold.

A two-layer neural network creates ___________ classifiers.

linear

For positive information gain, entropy should be _________ in child nodes compared to the parent node.

lower

Cognitive load refers to the total _____ required to learn new information.

mental effort

Which one of the following is NOT one of Duarte's 5 Rules of Data Slides?

mitigate chartjunk

KNN stands for K

nearest neighbor

Horizontal bar charts are recommended when showing _____ variables.

nominal

A primary key must be

non-empty & unique

The type of database relationship between a classroom switch and desktop computers is:

one-to-many

Vertical bar charts are used when showing:

ordinal columns

This returns all records from one table and only the matching records from the other table:

outer join

This cannot be duplicated in a database table:

primary key

There exists a database to track Soldier weapon qualifications. A Soldier qualifies many times throughout the year. The Soldier table uses the SSN as a primary key and is related to the WeaponQualification table. Which list of fields would be best for the WeaponQualification table?

qualificationID, soldierSSN, dateOfQualification, score, and weaponSerialNumber

In a table, another word for row is:

record

A _____ intelligently directs packets throughout a network based on their logical (IP) address.

router

Which is the most important attribute? f(x)= 3height - 1.2weight + age- 12speed + 13

speed

Pivot tables:

summarize data, can reorganize data from a table

A _____ makes forwarding decisions based on the physical address of a message.

switch

When the sender and receiver share the same key to scramble and unscramble a message, it's called:

symmetric key encryption

A confusion matrix shows __________.

the different kinds of errors

The primary purpose of a database is...

to organize data for easy search and retrieval

The primary purpose of a database is...

to organize data for easy search and retrieval of information.

To perform a math operation in a query, you should select:

totals

What is the major purpose of a primary key?

uniquely identify each record

A perfectly secure internet is not necessarily desirable because...

users would not be allowed to download or install anything onto their computers.

A field in a database table allows you to choose beef, chicken, or vegetarian. This mechanism is probably a:

value list lookup

With logistic regression, each attribute is assigned a ______ according to its importance in determining the classification.

weight

Given: f(x) = 100 + 8x1 - 4x2 + 3x3 - 12x4, what is the most important attribute?

x4

A perfectly ordered system has ______ entropy.

zero