Brainscape's Knowledge GenomeTM


Top Flashcards (Certified)
All Flashcards

AWS AI Certified Practitioner Study Notes > Udemy Test 1 > Flashcards

Udemy Test 1 Flashcards

1
Q

What is a token

A

A generative AI concept used to represent words, sub words or characters that a model processes as discrete units of text

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is Sampling Bias?

A

It occurs when the data used to train a model does not reflect the diversity of the real world population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is confirmation bias?

A

Selectively searching for or interpreting information to confirm existing beliefs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is observer bias?

A

Human errors or subjectivity during data analysis or observation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is measurement bias?

A

Inaccuracies in data collection

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is hallucination?

A

The model generates seemingly accurate information, that is incorrect

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is negative prompting?

A

Guiding a Gen AI model to avoid certain outputs, or behaviors when generating text

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is Sagemaker Clarify?

A

A tool to help explain how machine learning models make predictions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is Amazon Poly?

A

Used to deploy high quality natural sounding human voices in dozens of languages

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is Amazon Comprehend?

A

Uses machine learning to find insights and relationships in text

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is knowledge bases for Amazon Bedrock?

A

You can give foundational models and Agents contextual information from your companies private data sources for RAG to deliver more relevant, accurate and customized responses

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is BLEU

A

A metric that is designed to evaluate the quality of text that has been machine translated by comparing with reference translations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What can Amazon bedrock Guardrails do?

A

It can detect confidential information in prompts or model responses

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is Exploritory Data Analysis (EDA)?

A

A phase of the data science process that involves examining the data through Statistical Summeries and visualizations to identify patterns, detect anomalies and form a hypothesis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is Amazon Personalized?

A

A ML service that uses your data to generate product and content recommendations for your users

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Transformer models

A

Use a self attention mechanism and implement contextual ebbeddings

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What is Amazon Rekognition

A

A cloud based image and video service that makes it easy to add computer vision capabilities to your application

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Key features of Amazon Sagemaker Jumpstart

A
  • Pre-trained models that are fully customizable for your use case with your data
  • You can evaluate, compare, and select foundational models quickly based on Pre-Trained quality and responsibility metrics
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Narrowly defined use cases

A

Provide clear and specific requirements for the application, helping the research team understand exactly what the model need to accomplish

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Amazon OpenSearch Service

A

Is designed to provide fast search capabilities and supports full text search, indexing, and scoring

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

BERT

A

A model that is used to Differentiate the contextual meaning of words when applied to different phrases

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

AWS Global Infrastructure

A
  • Each availability zone has one or more data centers
  • Each AWS region has a minimum of 3 AZ’s
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Few Shot Prompting

A

Involves providing the model with a few examples that include user input and the correct user intent

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Plagiarism

A

Presenting someone else’s work, ideas or creations as your own. A concern that exists around AI

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Foundational models
Use self-supervised learning to create labels from input data
26
Fine Tuning a foundational model
Is a supervised learning process
27
Continued Pre-training
Uses Unlabeled data to pre-train a model
28
Fine Tuning
Uses labeled data to train a model
29
Testing and Deploying customized models for Bedrock
It is mandatory to use provisional throughput
30
Hyperparameter Tuning
Allows you to adjust settings such as reguklaization, learning rates, and drop out rates to enhance the models ability to generalize Local to new data
31
Asynchronous Inference
Allows you to process smaller payloads without requiring real-time responses by queuing requests and handling them in the background. It’s cost effective and efficient when a delay is acceptable
32
Valid use case for Gen AI
Create Photorealistic images from text descriptions is a valid use case
33
use MFLOW with Amazon Sagemaker:
To track, organize, view, analyze and compare iterative ML experimentation to gain insights and register and deploy models
34
Rag approach
The least costly and most efficient solution for providing up to date and relevant responses
35
What does Amazon Q business web application workflow use?
- Retrieval augmented Generation (RAG) - Large Language Model (LLM)
36
Approaches that are best for changing a Foundation Model(FM) into a domain specific expert
- Continual Pre-Training - Domain Adaptive Fine Tuning
37
What can Amazon Rekognition not be use for?
To create multilingual User Experiances
38
What do you use to get more creative responses from the same prompt in Bedrock?
Use higher Tempature
39
What is the Shared Security model for AWS
AWS is responsible for security of the cloud, while the user is responsible for security in the cloud
40
What is the best pricing cloud option for a company that is uncertain about the time or commitment or extent of use
On demand pricing
41
What are decision trees ?
Highly interpretable models that provide a clear and straightforward visualization of the decision making process
42
What are Agents for Amazon Bedrock?
Fully managed capabilities that make it easier for developers to create Generative AI based applications that can complete complex tasks for a wide range of use cases
43
What are Partial Dependable Plots(PDP)?
The provide a global view of a models behavior by showing how the model changes as a single feature is varied across it’s range
44
What is Amazon transcribe?
It converts audio input into text
45
What is amazon Comprehend
A virtual NLP (Natural Language Processing) service that uses machine learning to find insights and relationships in text
46
What is Generative AI
It encompasses models and algorithms capable of creating new content such as text, images and audio based on patterns learned from existing data
47
What is reinforcement learning?
It involves an agent interacting with an environment by taking actions and receiving rewards or penalties, learning to maximize cumulative rewards over time
48
What is invocation logging?
Allows for detailed logging of all requests and responses during model invocations
49
What is the default vector database for amazon bedrock
Opensearch serverless vector store
50
Confusion matrix
A tool designed to evaluate the performance of classification models by displaying the number of positives, negatives as well as false positives and false negatives
51
What is top P
The percentage of most likely candidates that a model considers for the next token
52
When using top p, how do you increase the size of the pool?
Choose a higher value
53
When using top P, how do you decrease the size of the pool
Choose a lower value to decrease the size of the pool and limit options to likely outputs
54
What is Amazon Kendra?
A highly accurate and easy to use search service
55
What powers Amazon Kendra?
Machine learning
56
What is a context window?
It defines how much text the AI Model can process process at one time to generate good output
57
What is Sagemaker model dashboard?
A centralized portal where you can view, search and explain all models in your account
58
What is Amazon Forecast?
A fully managed service that uses statistical and Machine Learning Algorithms to deliver highly accurate time series forecasts
59
What is Model evaluation?
The process of evaluating and comparing model output to determine the model that is best suited for a case
60
What is Model evaluation?
The process of evaluating and comparing model output to determine the model that is best suited for a case
61
What is model Inference?
The process of a model generating output from a given input
62
What is Top K?
The number of most likely candidates that the models consider for the next token
63
What is Supervised learning?
Algorithms that train on sample data that specifies the Algorithms input and output
64
What is Linear regression?
Refers to supervised learning models that predict a value from a continuous scale
65
What is a Neural network?
A more complex supervised learning technique
66
What is Amazon Q developer powered by?
Amazon Bedrock
67
How do you expose a model to a more diverse set of inputs?
By Augmenting Data
68
What is Amazon Comprehend ?
A Natural Language Processing(NLP) service that uses Machine Language to uncover insights and relationships in text
69
What is an AI service that provides access to foundation models via an API
Amazon Bedrock
70
What is a service that provides guidance to help you provision your resources following AWS best practices?
AWS Trusted Advisor
71
What is AWS trusted advisor?
A service that provides guidance to help you provision your resources using AWS best practices
72
What is the most effective way to minimize costs associated with the use of a Gen AI model in Bedrock?
Reduce the number of tokens in the input
73
Foundational Models
Serve as a broad base for various AI applications by providing generalized capabilities
74
What is Amazon Sagemaker ground truth?
It helps you to build high quality training datasets for your Machine learning models
75
What are the key components of a good prompting technique?
1. Instructions 2. Context 3. Input Data 4. Output indicator
76
What is Amazon Q?
A Generative AI powered assistant that allows you to create pre-packaged Gen AI applications
77
Amazon Bedrock provides what?
An environment to build and scale Gen AI applications using a foundation models via
78
What is Transfer learning?
A method that allows a model to utilize the knowledge learned from one task or dataset to improve it performance on a new, but related, task
79
Amazon bedrock is the easiest way to?
Build and scale generative AI Applications with foundation models
80
What is Amazon Sagemaker Jumpstart?
A machine learning hub with Foundation Models, Built in Algorithms, and pre-built ML solutions that you can deploy with just a few clicks.
81
What can Generative AI do?
It can automate the creation of new data based on existing patterns, enhancing productivity and innovation

AWS AI Certified Practitioner Study Notes (6 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions