Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

MLA-C01 > MLA-C01 > Flashcards

MLA-C01 Flashcards

Cert Exam Study

1
Q

Before you can use auto scaling, you must have already created an Amazon SageMaker ______________.

A

model endpoint.

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

You can have multiple model _____________for the same endpoint.

A

versions

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

Amazon SageMaker ____________ provides tools to help explain how machine learning (ML) models make predictions.

A

Clarify

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

An ____________can be thought of as the answer to a Why question that helps humans understand the cause of a prediction.

A

explanation

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

On AWS, AI/ML practitioners can use Amazon Sagemaker ____________, which uses Shapley values to help answer how different variables influence model behavior.

A

Clarify

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

Debug model output tensors from machine learning training jobs in real time and detect non-converging issues using Amazon SageMaker ____________.

A

Debugger

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

___________is the extent to which you can explain the internal mechanics of an ML or deep learning system in human terms.

A

Explainability

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

Amazon SageMaker _________produces metrics that measure the predictive quality of machine learning model candidates.

A

Autopilot

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

The ratio of the number of correctly classified items to the total number of (correctly and incorrectly) classified items.

A

Accuracy

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

measures how well an algorithm predicts the true positives (TP) out of all of the positives that it identifies.

A

Precision

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

uses natural language processing (NLP) to extract insights about the content of documents. It develops insights by recognizing the entities, key phrases, language, sentiments, and other common elements in a document.

A

Amazon Comprehend

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

a text translation service that uses advanced machine learning technologies to provide high-quality translation on demand. use to translate unstructured text documents or to build applications that work in multiple languages.

A

Amazon Translate

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

a fully managed, automatic speech recognition (ASR) service that makes it easy for developers to add speech to text capabilities to their applications.

A

Amazon Transcribe

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

a cloud service that converts text into lifelike speech. You can use to develop applications that increase engagement and accessibility.

A

Amazon Polly

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

a cloud-based image and video analysis service that makes it easy to add advanced computer vision capabilities to your applications.

A

Amazon Rekognition

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

a fully managed service that uses statistical and machine learning algorithms to deliver highly accurate time-series forecasts.

A

Amazon Forecast

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

an AWS service for building conversational interfaces for applications using voice and text.

A

Amazon Lex

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

a fully managed machine learning service that uses your data to generate item recommendations for your users. It can also generate user segments based on the users’ affinity for certain items or item metadata.

A

Amazon Personalize

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

a machine learning (ML) service that automatically extracts text, handwriting, and data from scanned documents.

A

Amazon Textract

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

an intelligent search service that uses natural language processing and advanced machine learning algorithms to return specific answers to search questions from your data.

A

Amazon Kendra

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

allows you to conduct a human review of machine learning (ML) systems to guarantee precision.

A

Amazon Augmented AI (A2I)

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

uses machine learning (ML) to make it easier for customers to accurately detect anomalies in their metrics.

A

Amazon Lookout for Metrics

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

a fully managed service enabling customers to identify potentially fraudulent activities and catch more online fraud faster.

A

Amazon Fraud Detector

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

a fully managed, generative-AI powered assistant that you can configure to answer questions, provide summaries, generate content, and complete tasks based on your enterprise data.

A

Amazon Q Business

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Amazon Polly is the Opposite of Amazon ____________.

A

Transcribe

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

______________measures how many actual positives were predicted as positive.

A

Recall

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

_____________is the harmonic mean of precision and recall.

A

F1-measure

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

It measures the ability of the model to predict a higher score for positive examples as compared to negative examples.

A

AUC (Area Under Curve)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

_________is a method used in machine learning to reduce errors in predictive data analysis.

A

Boosting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

____________improves machine models’ predictive accuracy and performance by converting multiple weak learners into a single strong learning model.

A

Boosting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

____________ are data structures in machine learning that work by dividing the dataset into smaller and smaller subsets based on their features

A

Decision trees

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

Boosting creates an ____________model by combining several weak decision trees sequentially.

A

ensemble

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

In ________, data scientists improve the accuracy of weak learners by training several of them at once on multiple datasets. In contrast, boosting trains weak learners one after another.

A

bagging

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

__________is a popular and efficient open-source implementation of the gradient boosted trees algorithm.

A

XGBoost

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
35
Q

___________boosting is a supervised learning algorithm that tries to accurately predict a target variable by combining multiple estimates from a set of simpler models.

A

Gradient

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
36
Q

Amazon SageMaker _____________ reduces data prep time for tabular, image, and text data from weeks to minutes.

A

Data Wrangler

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
37
Q

With SageMaker ________________ you can simplify data preparation and feature engineering through a visual and natural language interface.

A

Data Wrangler

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
38
Q

Sagemaker ____________ a no-code ML tool that helps business analysts generate accurate ML predictions without having to write code or without requiring any ML experience.

A

Canvas

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
39
Q

Amazon SageMaker ____________ is a fully managed, purpose-built repository to store, share, and manage features for machine learning (ML) models.

A

Feature Store

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
40
Q

___________are inputs to ML models used during training and inference.

A

Features

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
41
Q

SageMaker ____________ tags and indexes feature groups so they are easily discoverable through the visual interface of Amazon SageMaker Studio.

A

Feature Store

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
42
Q

Amazon SageMaker ____________ offers the most comprehensive set of human-in-the-loop capabilities, allowing you to harness the power of human feedback across the ML lifecycle to improve the accuracy and relevancy of models.

A

Ground Truth

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
43
Q

You can complete a variety of human-in-the-loop tasks with SageMaker ___________, from data generation and annotation to model review, customization, and evaluation, either through a self-service or an AWS-managed offering.

A

Ground Truth

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
44
Q

SageMaker _________helps identify potential bias during data preparation without writing code.

A

Clarify

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
45
Q

SQL function used for anomaly detection on numeric columns in a stream

A

RANDOM_CUT_FOREST

46
Q

is derived from “Linux” and “cluster

A

Lustre

47
Q

a type of parallel distributed file system, for large-scale computing

A

Lustre

48
Q

a fully managed Windows file system share drive

A

FSx for Windows File Server

49
Q

a network drive you can attach to your instances while they run

A

EBS

50
Q

Managed NFS (network file system) that can be mounted on many EC2

A

EFS

51
Q

Data Warehouse vs Data Lake. Warehouse is ________________. Lake is ___________

A

Structured, Unstructured

52
Q

Binary format that stores both the data and its schema

A

AVRO

53
Q

Columnar storage format optimized for analytics.

A

Parquet

54
Q

Find K “nearest” (most similar) rows and average their values

A

K Nearest Neighbor (KNN)

55
Q

Find linear or non-linear relationships between the missing feature and other features

A

Regression

56
Q

Duplicate samples from the minority class

A

Oversampling

57
Q

Instead of creating more positive samples, remove negative ones

A

Undersampling

58
Q

measures how “spread-out” the data is

A

Variance

59
Q

________________ 𝜎 is just the square root of the variance.

A

Standard Deviation

60
Q

Data points that lie more than one ___________________ from the mean can be considered unusual.

A

Standard Deviation

61
Q

Bucket observations together based on ranges of values.

A

Binning

62
Q

Create “buckets” for every category * The bucket for your category has a 1, all others have a 0

A

One Hot Encoding

63
Q

______________ for deploying to edge devices

A

SageMaker NEO

64
Q

___________values are the algorithm used to determine the contribution of each feature toward a model’s predictions

A

Shapley

65
Q

Used on the final output layer of a
multi-class classification problem

A

Softmax

66
Q

Choosing an activation function: For multiple classification, use _________on the output layer

A

softmax

67
Q

Choosing an activation function: ________do well with Tanh

A

RNN’s

68
Q

Choosing an activation function: For everything else

A

Start with ReLU

69
Q

Choosing an activation function: _________for really deep networks

A

Swish

70
Q

When you have data that doesn’t
neatly align into columns
* Images that you want to find features
within
* Machine translation
* Sentence classification
* Sentiment analysis

A

Convlution Neural Network (CNN)

71
Q

RNN’s: what are they for?

A

Time-series data

72
Q

When you want to predict future behavior based
on past behavior

A

Recurrent Neural Network (RNN)

73
Q

Sequence to sequence, Sequence to vector, Vector to sequence, Encoder -> Decoder

A

RNN topologies

74
Q

_________batch sizes tend to not get stuck in local minima

A

Small

75
Q

____________batch sizes can converge on the wrong solution at
random

A

Large

76
Q

_________learning rates can overshoot the correct solution

A

Large

77
Q

____________learning rates increase training time

A

Small

78
Q
  • ________________techniques are
    intended to prevent overfitting.
A

Regularization

79
Q

Preventing overfitting in ML in general
* A regularization term is added as
weights are learned

A

L1 and L2 Regularization

80
Q
  • L1: sum of _______________
A

weights

81
Q

L2: sum of ______________

A

square of weights

82
Q

We need to understand true
positives and true negative, as well
as false positives and false
negatives.

A

confusion matrix

83
Q

Percent of positives rightly predicted

A

Recall

84
Q

AKA Correct Positives

A

Precision

85
Q

Plot of true positive rate (recall) vs. false
positive rate at various threshold settings.

A

ROC Curve

86
Q

The area under the ROC curve is… wait
for it..

A

AUC

87
Q

Generate N new training sets by random sampling with
replacement

A

Bagging

88
Q

Training is sequential; each classifier takes into account the
previous one’s success.

A

Boosting

89
Q

Define the hyperparameters you care about and the ranges you
want to try, and the metrics you are optimizing for

A

Automatic Model Tuning

90
Q

Don’t optimize too many hyperparameters at once
* Limit your ranges to as small a range as possible
* Use logarithmic scales when appropriate
* Don’t run too many training jobs concurrently
* This limits how well the process can learn as it goes
* Make sure training jobs running on multiple instances report the
correct objective metric in the end

A

Automatic Model Tuning: Best Practices

91
Q

Stop training in a tuning job early if it is not improving the
objective significantly

A

Early Stopping

92
Q

Uses one or more previous tuning jobs as a starting point

A

Warm Start

93
Q

Automates:
* Algorithm selection
* Data preprocessing
* Model tuning
* All infrastructure
* It does all the trial & error for you

A

SageMaker Autopilot

94
Q

Visual IDE for machine learning

A

SageMaker Studio

95
Q

Create and share
Jupyter notebooks with
SageMaker Studio
* Switch between
hardware configurations
(no infrastructure to
manage)

A

SageMaker Notebooks

96
Q

Organize, capture, compare, and search your ML jobs

A

SageMaker Experiments

97
Q

Saves internal model state at periodical intervals
* Gradients / tensors over time as a model is trained
* Define rules for detecting unwanted conditions while training
* A debug job is run for each rule you configure
* Logs & fires a CloudWatch event when the rule is hit

A

SageMaker Debugger

98
Q

Catalog your models, manage model
versions
* Associate metadata with models
* Manage approval status of a model
* Deploy models to production
* Automate deployment with CI/CD

A

SageMaker Model Registry

99
Q

___________________ is a visualization
toolkit for Tensorflow or PyTorch
* Visualize loss and accuracy
* Visualize model graph
* View histograms of weight, biases over
time
* Project embeddings to lower
dimensions
* Profiling

A

Tensorboard

100
Q

Compile & optimize training jobs on GPU instances
* Can accelerate training up to 50%
* Converts models into hardware-optimized instructions
* Tested with Hugging Face transformers library, or bring your own model
* Incompatible with SageMaker distributed training libraries

A

SageMaker Training Compiler

101
Q

Retain and re-use provisioned
infrastructure
* Useful if repeatedly training a model to
speed things up
* Use by setting
KeepAlivePeriodInSeconds in your
training job’s resource config

A

Warm Pools

102
Q

Creates snapshots during your training
* You can re-start from these points if necessary
* Or use them for troubleshooting, to analyze the model at different
points
* Automatic synchronization with S3 (from /opt/ml/checkpoint)

A

Checkpointing

103
Q

Run automatically when using ml.g or
ml.p instance types
* Replaces any faulty instances
* Runs GPU health checks
* Ensures NVidia Collective
Communication Library is working

A

Cluster Health Checks and Automatic
Restarts

104
Q

You can of course run multiple
training jobs in parallel
* “job parallelism”
* Individual training can also be
parallelized
* Distributed data parallelism
* Distributed model parallelism

A

Distributed Training

105
Q

Network device attached to your
SageMaker instances
* Makes better use of your bandwidth
* Promises performance of an onpremises High Performance
Computing (HPC) cluster in the cloud

A

Elastic Fabric Adapter (EFA)

106
Q

______________ produces a
weighted average of all
token embeddings. The
magic is in computing the
attention weights.

A

Self-attention

107
Q

A mask can be applied
to prevent tokens from
“peeking” into future
tokens (words)

A

Masked Self-Attention

108
Q

Chat!
* Question answering
* Text classification
* i.e., sentiment analysis
* Named entity recognition
* Summarization
* Translation
* Code generation
* Text generation
* i.e., automated customer service

A

Applications of Transformers

109
Q

Tokenization, token encoding
* Token embedding
* Captures semantic relationships
between tokens, token similarities
* Positional encoding
* Captures the position of the token
in the input relative to other nearby
tokens
* Uses an interleaved sinusoidal
function so it works on any length

A

LLM Input processing

110
Q

The stack of decoders outputs a
vector at the end
* Multiply this with the token
embeddings
* This gives you probabilities
(logits) of each token being the
right next token (word) in the
sequence

A

LLM Output processing

111
Q
A

MLA-C01 (3 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions