Weekend Sale - Special 70% Discount Offer - Ends in 0d 00h 00m 00s - Coupon code: 70dumps

AIP-210 Questions and Answers

Question # 6

Which of the following text vectorization methods is appropriate and correctly defined for an English-to-Spanish translation machine?

A.

Using TF-IDF because in translation machines, we do not care about the order of the words.

B.

Using TF-IDF because in translation machines, we need to consider the order of the words.

C.

Using Word2vec because in translation machines, we do not care about the order of the words.

D.

Using Word2vec because in translation machines, we need to consider the order of the words.

Full Access
Question # 7

Which of the following describes a neural network without an activation function?

A.

A form of a linear regression

B.

A form of a quantile regression

C.

An unsupervised learning technique

D.

A radial basis function kernel

Full Access
Question # 8

For a particular classification problem, you are tasked with determining the best algorithm among SVM, random forest, K-nearest neighbors, and a deep neural network. Each of the algorithms has similar accuracy on your data. The stakeholders indicate that they need a model that can convey each feature's relative contribution to the model's accuracy. Which is the best algorithm for this use case?

A.

Deep neural network

B.

K-nearest neighbors

C.

Random forest

D.

SVM

Full Access
Question # 9

Which of the following tools would you use to create a natural language processing application?

A.

AWS DeepRacer

B.

Azure Search

C.

DeepDream

D.

NLTK

Full Access
Question # 10

Which of the following is NOT an activation function?

A.

Additive

B.

Hyperbolic tangent

C.

ReLU

D.

Sigmoid

Full Access
Question # 11

An AI practitioner incorporates risk considerations into a deployment plan and decides to log and store historical predictions for potential, future access requests.

Which ethical principle is this an example of?

A.

Fairness

B.

Privacy

C.

Safety

D.

Transparency

Full Access
Question # 12

Which of the following scenarios is an example of entanglement in ML pipelines?

A.

Add a new method for drift detection in the model evaluation step.

B.

Add a new pipeline for retraining the model in the model training step.

C.

Change in normalization function in the feature engineering step.

D.

Change the way output is visualized in the monitoring step.

Full Access
Question # 13

Which of the following items should be included in a handover to the end user to enable them to use and run a trained model on their own system? (Select three.)

A.

Information on the folder structure in your local machine

B.

Intermediate data files

C.

Link to a GitHub repository of the codebase

D.

README document

E.

Sample input and output data files

Full Access
Question # 14

Which two of the following decrease technical debt in ML systems? (Select two.)

A.

Boundary erosion

B.

Design anti-patterns

C.

Documentation readability

D.

Model complexity

E.

Refactoring

Full Access
Question # 15

Which of the following algorithms is an example of unsupervised learning?

A.

Neural networks

B.

Principal components analysis

C.

Random forest

D.

Ridge regression

Full Access
Question # 16

The graph is an elbow plot showing the inertia or within-cluster sum of squares on the y-axis and number of clusters (also called K) on the x-axis, denoting the change in inertia as the clusters change using k-means algorithm.

What would be an optimal value of K to ensure a good number of clusters?

A.

2

B.

3

C.

5

D.

9

Full Access
Question # 17

When should you use semi-supervised learning? (Select two.)

A.

A small set of labeled data is available but not representative of the entire distribution.

B.

A small set of labeled data is biased toward one class.

C.

Labeling data is challenging and expensive.

D.

There is a large amount of labeled data to be used for predictions.

E.

There is a large amount of unlabeled data to be used for predictions.

Full Access
Question # 18

Which of the following best describes distributed artificial intelligence?

A.

It does not require hyperparemeter tuning because the distributed nature accounts for the bias.

B.

It intelligently pre-distributes the weight of starting a neural network.

C.

It relies on a distributed system that performs robust computations across a network of unreliable nodes.

D.

It uses a centralized system to speak to decentralized nodes.

Full Access
Question # 19

In general, models that perform their tasks:

A.

Less accurately are less robust against adversarial attacks.

B.

Less accurately are neither more nor less robust against adversarial attacks.

C.

More accurately are less robust against adversarial attacks.

D.

More accurately are neither more nor less robust against adversarial attacks.

Full Access
Question # 20

An organization sells house security cameras and has asked their data scientists to implement a model to detect human feces, as distinguished from animals, so they can alert th customers only when a human gets close to their house.

Which of the following algorithms is an appropriate option with a correct reason?

A.

A decision tree algorithm, because the problem is a classification problem with a small number of features.

B.

k-means, because this is a clustering problem with a small number of features.

C.

Logistic regression, because this is a classification problem and our data is linearly separable.

D.

Neural network model, because this is a classification problem with a large number of features.

Full Access
Question # 21

You train a neural network model with two layers, each layer having four nodes, and realize that the model is underfit. Which of the actions below will NOT work to fix this underfitting?

A.

Add features to training data

B.

Get more training data

C.

Increase the complexity of the model

D.

Train the model for more epochs

Full Access
Question # 22

You are building a prediction model to develop a tool that can diagnose a particular disease so that individuals with the disease can receive treatment. The treatment is cheap and has no side effects. Patients with the disease who don't receive treatment have a high risk of mortality.

It is of primary importance that your diagnostic tool has which of the following?

A.

High negative predictive value

B.

High positive predictive value

C.

Low false negative rate

D.

Low false positive rate

Full Access
Question # 23

Which of the following is a type 1 error in statistical hypothesis testing?

A.

The null hypothesis is false, but fails to be rejected.

B.

The null hypothesis is false and is rejected.

C.

The null hypothesis is true and fails to be rejected.

D.

The null hypothesis is true, but is rejected.

Full Access
Question # 24

Which of the following is the primary purpose of hyperparameter optimization?

A.

Controls the learning process of a given algorithm

B.

Makes models easier to explain to business stakeholders

C.

Improves model interpretability

D.

Increases recall over precision

Full Access
Question # 25

A change in the relationship between the target variable and input features is

A.

concept drift.

B.

covariate shift.

C.

data drift.

D.

model decay.

Full Access
Question # 26

Which of the following approaches is best if a limited portion of your training data is labeled?

A.

Dimensionality reduction

B.

Probabilistic clustering

C.

Reinforcement learning

D.

Semi-supervised learning

Full Access
Question # 27

Which of the following statements are true regarding highly interpretable models? (Select two.)

A.

They are usually binary classifiers.

B.

They are usually easier to explain to business stakeholders.

C.

They are usually referred to as "black box" models.

D.

They are usually very good at solving non-linear problems.

E.

They usually compromise on model accuracy for the sake of interpretability.

Full Access