Question 1

How would you differentiate between deep learning and traditional machine learning? (Select two)

Options :

A : Deep learning is a subset of machine learning that uses neural networks with many layers to learn from large amounts of data, while traditional machine learning algorithms often require feature extraction and can use various methods such as decision trees or support vector machines

B : In traditional machine learning, a data scientist manually determines the set of relevant features that the software must analyze, whereas in deep learning, the data scientist gives only raw data to the software and the deep learning network derives the features by itself

C : Traditional machine learning algorithms are only used for supervised learning tasks, whereas deep learning algorithms are only used for unsupervised learning tasks

D : Deep learning models are always faster to train than traditional machine learning models, regardless of the dataset size

E : Deep learning models do not require any data preprocessing, while traditional machine learning models require extensive data preprocessing

Answer: A,B

Question 2

A company is using Amazon Bedrock and it wants to set an upper limit on the number of tokens returned in the model's response.

Which of the following inference parameters would you recommend for the given use case?

Options :

A : Response length

B : Stop sequence

C : Top P

D : Top K

Answer: A

Question 3

A manufacturing company aims to leverage Amazon Bedrock to create a generative AI application that automates the monitoring of inventory levels, sales data, and supply chain information. The application should also recommend optimal reorder points and quantities to enhance operational efficiency.

What do you recommend?

Options :

A : Watermark detection for Amazon Bedrock

B : Agents for Amazon Bedrock

C : Guardrails for Amazon Bedrock

D : Knowledge Bases for Amazon Bedrock

Answer: B

Question 4

Which benefits might persuade a developer to choose a transparent and explainable machine learning model? (Select two)

Options :

A : They require less computational power and storage

B : They simplify the integration process with other systems

C : They facilitate easier debugging and optimization

D : They enhance security by concealing model logic

E : They foster trust and confidence in model predictions

Answer: C,E

Question 5

A company wants to use Amazon Bedrock for several use cases involving text generation as well as image generation. Which of the following Foundation Models do you recommend?

Options :

A : Jurassic

B : Claude

C : Amazon Titan

D : Llama

Answer: C

Free AIF-C01 Mock Exam – Practice Online Confidently

Buying Options: