Brainscape's Knowledge GenomeTM

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


See full index

AI 900 > Examquestions > Flashcards

Examquestions Flashcards

1
Q

What is Artificial Intelligence?

A

Machines that perform jobs that mimic human behavior

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

What is Machine Learning?

A

Machines that get better at a task without explicit programming

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

What is deep learning?

A

Machines that have an artificial neural network inspired by the human brain to solve complex problems

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

What are key elements to AI?

A

Machine Learning: foundation of an AI system to learn and predict human behaviour

Anomaly detection: detect outliers

Computer Vision: see like a human

Natural language processing: process human language with context

Conversational AI: hold a conversation like a human

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

What is a dataset?

A

logical grouping of units of data that have the same data structure to train

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

What is Data labeling?

A

identifying raw data and adding labels to provide context to help the machine learn

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

What is Supervised Learning?

A

You know the labels and have a precise output you want

make a prediction

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

What is Unsupervised learning?

A

labels are not known and the outcome does not need to be precise

recognize a structure or pattern

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

What is Reinforcement Learning?

A

No data and a ML model generates data to reach a goal

Game AI

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

What are Neural Networks?

A

algorithm to represent a brain
connections between neurons are weighted with multiple layers

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

What is deep learning?

A

A neural network with 3 or more layers

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

What is feed forward?

A

Neural Network where connections between nodes dont form a cycle

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

What is backpropagation? (BP)

A

backward movement though a neural network to adjust weights to improve the outcome on the next iteration - this is how it learns

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

What is the ground truth?

A

the answer/reality you want to reach with the model

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

What is a loss function?

A

compares the ground truth to the prediction to determine the error rate

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

Why are GPUs used for machine learning?

A

they can perform parallel operations on multiple sets of data - can have thousands or processor cores

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

What is forecasting?

A

makes a future prediction with relevant data

“analysis of trends”

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

What is a prediction?

A

makes a future prediction without relevant data

uses statistics to predict future outcomes

more guessing than forecasting

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

What are internal Evaluation metrics for an ML model?

A

Accuracy, F1 score, Precision, Recall

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

What are the external Evaluation metrics for an ML model?

A

metrics used to evaluate the final prediction of the ML model

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

What is Jupyter Notebook/Lab?

A

web-based application for authoring documents with live-code
text
visualizations etc.

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

What is Regression?

A

process of finding a function to correlate a labeled labeled dataset into continuous variable/number - make a prediction into the future

distance from the vector to the regression line is called error

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

What is classification?

A

finding a function to divide a labeled dataset into classes/categories

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

What is clustering?

A

grouping unlabeled data based on similarities and differences

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

What is a confusion matrix?

A

visualize the model predictions vs ground truth labels (actual)

also called error matrix

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

What Anomaly detection?

A

process of finding an outlier in a dataset

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

What is Computer Vision?

A

gain level of understanding digital images and video

Convolutional neural network: image and video recognition
recurrent neural network: handwriting or speech recognition
Semantic Segmentation: identify segments or objects
Image analysis: analyse image or video and apply label

28
Q

What is natural language processing?

A

understand the context of a corpus

analyzes text and interpret etc.

29
Q

What is conversational AI?

A

Chatbots, Voice Assistants etc.

Online Customer Support
HR processes
Health Care
IoT etc.

30
Q

What is Responsible AI? What are the principles?

A

ethical, transparent and accountable AI

  1. Fairness - should treat all people fairly
  2. Reliability and Safety
  3. Privacy and Security
  4. Inclusiveness
  5. Transparency
  6. Accountability
31
Q

What is Azure Cognitive Services?

A

comprehensive family of AI services and cognitive APIs to help you build intelligent apps

deploy with containers, with not much expertise

32
Q

What is part of Azure Cognitive Services?

A

Decision:
Anomaly Detector
Content Moderator
Personaliser

Language:
Language Understanding
QnA Maker
Text Analytics
Translator

Speech:
Speech to Text
Text to Speech
Speech Translation
Speaker Recognition

Vision:
Computer Vision
Custom Vision
Face Detection

33
Q

What is Knowledge Mining?

A

Knowledge Mining is a discipline that uses a combination of intelligent services to quickly learn from vast amounts of information

34
Q

What are text analytics and what is part of it?

A

Sentiment Analysis
Opinion Mining
Key Phrase Extradiction
Language Detection
Named entity recognition

35
Q

What are important infos to the Form Recognizer Service?

A

trained with own data
only needs five sample input forms to start
can use it to extract data from forms

36
Q

What are the key parts LUIS reads out of a text?

A

Intention
Entities what parts of the intent is used to determine the answer
utterance: the user input

37
Q

What is the Azure Bot Service?

A

Intelligent, serverless bot service that scales on demand - is used for creating, publishing and managing bots

38
Q

What is Bot Framework Composer?

A

opensource IDE for developers to create conversational experiences (bots)

has templates and can author, test, provision and manage solutions

39
Q

What is Azure Machine Learning Services?

A

Service to run workloads
Jupyter Notebooks
Azure Machine Learning Python: code
MLOps: automation for creation
Azure Machine Learning Designer: no code
Data Labeling Service: ask humans to label data
Responsible Machine Learning

40
Q

Whats part of author in Azure Machine Learning Studio?

A

Notebooks: write python code to built models
AutoML: auto building of models (limited)
Designer: No Code Designer to construct ML

41
Q

Whats part of Assets in Azure Machine Learning Studio?

A

Datasets
Experiments
Pipelines
Models
Endpoints

42
Q

What is part of “manage” in Azure Machine Learning Studio?

A

Compute
Environments
Datastores
Data Labeling
Linked Services

43
Q

What are the four kinds of compute to choose in Azure Machine Learning Studio?

A

Compute Instances: development workstations
Compute Clusters: scalable virtual machines
Inference Clusters: deployment targets for services
Attached Compute: links to exisiting azure resources

44
Q

What options are there for labeling in Machine Learning Studio?

A

Human labeling
Machine learning assisted data labeling

45
Q

What are the two ways to build pipelines?

A

Azure Machine Learning Designer
Azure Machine Learning Python SDK

46
Q

What is Model Registry?

A

management tool for your models

47
Q

What is Azure ML Endpoints?

A

service that allows you to deploy machine learning models as a web service

48
Q

If you deploy a model over Endpoints what Compute types are used?

A

Containers or Kubernetes

49
Q

What is AutoML?

A

automates the creation of an ML model

50
Q

What is Data Guard Rails in AutoML

A

service that ensures high quality for the input data

51
Q

What scaling or normalization techniques are available in AutoML?

A

StandardScaleWrapper: normalizes values for better performance
MinMaxScalar: transforms features according to min and max value
RobustScalar: Scales features by their quantile range
Principal component analysis: reduces the labels
TruncatedSVDWrapper: reduces complexity but without centering the data first
SparseNormalizer: similar

52
Q

What is the Model Selection within AutoML?

A

service that helps you select the best performing statistical model

53
Q

What are classification metrics?

A

For well-balanced datasets:
accuracy
average_precision_score_weighted
norm_macro_recall
precision_score_weighted

imbalanced:
AUC_weighted

54
Q

What is a well-balanced/imbalanced dataset?

A

well-balanced: evenly distributed values
imbalanced: some values very often, others are scarce

55
Q

What are primary metrics for Regression Scenarios?

A

large range:
spearman_correlation
r2_score

small range:
normalized_root_mean_squared_error
normalized_mean_absolute_error

56
Q

What is Model Validation?

A

Compares how good the model “learned” by comparing the results from a training dataset with a test dataset

57
Q

What is custom vision?

A

no-code service to build Classification and Object Detection ML Models

58
Q

Custom Vision - What Classification Domains are recommended for which size of datasets?

A

bigger datasets:
General
General A1

smaller datasets:
General A2

59
Q

Custom Vision - How many images do you need per label to train?

A

15

60
Q

Custom Vision - What are evaluation metrics?

A

Precision: accuracy
Recall: How many relevant iteams returned?
Average Precision

For object detection: mean average precision

61
Q

What should Kubernetes and what should Containers be used for?

A

Kubernetes: Deployment
Containers: Dev/Testing

62
Q

What are labels and features?

A

Feature: Nebenwerte um auf den zu schätzenden Wert zu schließen

Label: der Wert der geschätzt wird

63
Q

What is the difference between clustering and categorizing?

A

Cluster: ähnliche Werte zusammen in Kategorien bringen

Categorizing: Werte anhand von festen Labeln zuordnen

64
Q

Was sind Metriken um Regression zu bewerten?

A

R2
RMSE

65
Q

What Metric for classification models?

A

true positive rate

66
Q

Kann Custom Vision service für Videos benutzt werden?

A

Nein

67
Q
A

AI 900 (1 decks)

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