ExamTopics Flashcards

Master all 126 Questions

1
Q

EXPLAINABILITY

A

PDP - PARTIAL DEPENDENCE PLOTS

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

LEGAL DOCUMENTS STUDY

A

SUMMARIZATION CHATBOT

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

20 CATEGORIES HUMAN GENES

A

DECISION TREES

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

PLANT DISEASES

A

ACCURACY

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

SMALL LLM OUTPUTS WRITTEN IN SPECIFIC LANGUAGE

A

ADJUST THE PROMPT

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

1GB PROCESSING TIME 1 HOUR NEAR REAL TIME

A

ASYNCHRONOUS INFERENCE

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

TRAIN LLM BUT NOT FROM SCRATCH

A

TRANSFER LEARNING

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

EYEWARE

A

HUMAN IN THE LOOP VALIDATION

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

ENCRYPTION S3 BUCKET - BEDROCK MODEL

A

BEDROCK - ASSUMES THE CORRECT ROLE

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

EDGE DEVICE LLMS

A

OPTIMIZED SLMS

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

SHARE AND MANAGE VARIABLES - AMAZON SAGEMAKER

A

SAGEMAKER FEATURE STORE

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

DEVELOPER PRODUCTIVITY

A

AMAZON Q - SOFTWARE SNIPPETS

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

NO DATA ALLOWED ON INTERNET

A

AWS PRIVATELINK

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

GREEN, YELLOW MARBLES PROBABILITY

A

SIMPLE RULES TO CALCULATE

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

Runtime Efficiency Metrics

A

Average Response Time

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

CONTACT CENTER CUSTOMER CONVERSATIONS AUDIO FILES ANALYZE.

A

AWS TRANSCRIBE

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

PETABYTES..AD CAMPAIGN. UNLABELED

A

UNSUPERVISED LEARNING

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

SEARCH - TEXT AND IMAGES

A

MULTIMODAL EMBEDDING MODEL

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

FINE TUNE FOUNDATIONAL MODEL

A

LABELED DATA WITH PROMPT FIELD AND COMPLETION FIELD

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

AI TO PROTECT FROM THREATS, IP - SUSPICIOUS

A

ANOMALY DETECTION

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

AMAZON OPENSEARCH - VECTOR DATABASE APPS

A

SCALABLE INDEX AND NEAREST NEIGHBOUR SEARCH CAPABILITY

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

USE CASE OF GENAI

A

PHOTOREALISTIC IMAGES

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

HOW MUCH INFO CAN FIT INTO ONE PROMPT

A

CONTEXT WINDOW

24
Q

ADHERE TO COMPANY TONE

A

EXPERIMENT AND REFINE THE PROMPT UNTIL DESIRED

25
Q

SENTIMENT ANALYSIS..CLASSIFY AS POSITIVE AND NEGATIVE

A

POSITIVE AND NEGATIVE LABELS IN PROMPT (FOLLOWED BY NEW TEXT PASSAGE TO BE CLASSIFIED)

26
Q

IDENTIFY UNAUTHORIZED USE

A

CLOUDTRAIL

27
Q

NO UNDERLYING INFRASTRUCTURE

A

SAGEMAKER SERVERLESS INFERENCE

28
Q

ISVs - INDEPENDENT SOFTWARE VENDORS

A

ARTIFACT

29
Q

29..PREVENT EXPOSE SENSITIVE INFORMATION

A

PROMPT TEMPLATE - DETECT ATTACK PATTERNS

30
Q

security scoping matrix..MOST OWNERSHIP

A

No THIRD PARTY..CUSTOMER OWNS - FROM SCRATCH

31
Q

ANIMAL PHOTOS…AUTOMATIC DETECTION

A

OBJECT DETECTION

32
Q

BEDROCK..WITHOUT LONG TERM COMMITMENT..LIMITED BUDGET

A

ON-DEMAND

33
Q

QUICKLY DEPLOY AND CONSUME FM IN VPC

A

SAGEMAKER JUMPSTART

34
Q

SECURELY USE BEDROCK

A

IAM, LEAST PREVILEGE

35
Q

EMPLOYEES..MINIMAL EXPERIENCE

A

GENERATIVE PRE-TRAINED TRANSFORMERS(gpt)

36
Q

36)NEW OBJECTS detection IN IMAGE USES

A

INFERENCE

37
Q

BIAS IN THE HUMAN IMAGES…HOW TO ADDRESS

A

DATA AUGMENTATION FOR IMBALANCED CLASSES

38
Q

TITAN FM..SUPPLEMENT DATA BY COMPANY PRIVATE DATA SOURCES

A

CREATE BEDROCK KNOWLEDGE BASE

39
Q

MEDICAL COMP. NEEDS TRANSPARENCY TO MEET REGULATORY REQ.

A

SIMPLE METRICS, REPORTS SAGEMAKER CLARIFY.

40
Q

SAGEMAKER JUMPSTART MODEL..MUST COMPLY MULTIPLE REGULATORY FRAMEWORKS.

A

THREAT DETECTION
DATA PROTECTION

41
Q

INCREASE ACCURACY TO SPECIFIC ACCEPTANCE LEVEL

A

INCREASE EPOCHS

42
Q

DECREASE NU OF EMPLOYEES.

A

LOOK AT AHT OR AVERAGE CALL DURATION.

43
Q

AMAZON CLARIFY

A

ADDRESSES BIAS DURING DATA PREP

44
Q

PREDICT PRICES..NOT WORKING WELL IN PRODUCTION.

A

INCREASE THE VOL OF DATA USED IN TRAINING.

45
Q

CUSTOMER SENTIMENTS BASED ON CUSTOMER REVIEWS

A

AMAZON COMPREHEND, BEDROCK

46
Q

PRODUCT MANUALS PDF

A

UPLOAD TO BEDROCK KNOWLEDGE BASE

47
Q

CONTENT MODERATION - LEAST EFFORT

A

BENCHMARK DATASETS

48
Q

48)MARKETING CAMPAIGNS..BRAND ALIGNMENT

A

CREATE EFFECTIVE PROMPTS

49
Q

LOAN COMPANY..DISCOUNTS

A

DETECT IMBALANCES DISPARITIES, MODEL BEHAVIOR..TRANSPARENCY..STORMY :)

50
Q

IMPROVE SUMMARIZATION QUALITY

A

BUY PROVISIONED THRUPUT

51
Q

CHOOSE MODEL THAT EMPLOYEES PREFER

A

HUMAN WORKFORCE

52
Q

STUDENT COPIES GENAI STUFF..PROBLEM

A

PLAGIARISM

53
Q

EC2 WITH LEAST ENVIRONMENTAL EFFECT

A

EC2 TRN SERIES

54
Q

STORIES BASED ON CLASSICS STORIES. APPROPRIATE FOR CHILDREN.

A

GUARDRAILS FOR BEDROCK

55
Q
A