1what is AI?
this is a software that imitates human behavior and capabilities.
2Machine Learning, Computer Vision, Natural Language Processing, Document Intelligence, Knowledge Mining, and Generative AI are all what?
Key AI Workloads
3This is often the foundation for an AI system, and is the way we 'teach' a computer model to make predictions and draw conclusions from data?
machine learning
4capabilities within AI to interpret the world visually through cameras, video, and images?
computer vision
5capabilities within AI that deal with managing, processing, and using high volumes of data found in forms and documents?
document intelligence
6capabilities within AI to extract information from large volumes of often unstructured data to create a searchable knowledge store?
knowledge mining
7capabilities within AI that create original content in variety of formats including natural language, image, code and more?
generative ai
8machine learning is the _______ for most AI solutions?
foundation
9this is a cloud-based platform for creating, managing, and publishing machine learning models?
microsoft azure machine learning service
10this is a part of the azure machine learning studio that allows non-experts to quickly create an effective machine learning model from data?
automated machine learning
11this is a part of the azure machine learning studio that is a graphical interface enabling no-code development of machine learning solutions?
azure machine learning designer
12this is a part of the azure machine learning studio that allows people to analyze and optimize your experiments with visualizations
data metric visualization
13this is a part of the azure machine learning studio that allows you to write and run your own code in managed jupyter notebook servers that are directly integrated into the studio
notebooks
14what is the area of AI that deals with visual processing?
computer vision
15computer vision tasks include?
Image classification, object detection, semantic segmentation, image analysis, face detection, analysis and recognition, optical character recognition (ORC)
16this involves training a MLM to classify images based on their content?
image classification
17these MLMs are trained to classify individual objects within an imager, and identify their location within a bounding box?
object detection
18this is an advanced machine learning technique in which individual pixels in the image are classified according to the object to which they belong?
semantic segmentation
19this allows you to create solutions that combine MLMs advanced image analysis techniques to extract info from images, including 'tags' that could help catalog the image or descriptive caption that summarizes the scene shown in image?
image analysis
20this is a specialized form of object detection that locates human faces in an image?
face detection, analysis, and recognition
21this is a technique used to detect and read text in images, you can sue this to read text in photos or to extract info from scanned documents, letters, invoices or forms
optical character recognition
22what azure service can you use to devlop computer vision solutions?
microsoft azure ai vision
23this is the environment where you can test azure ai vision
azure vision studio
24azure ai vision includes
image analysis, face, and ocr
25in azure you can use this to build face detection and recognition solutions
face
26enables you to create software that can:
analyze and interpret text in documents, email messages, and other sources.
interpret spoken language and synthesize speech responses
automatically translate spoken or written phrases between languages
interpret commands and determine appropriate actions
NLP
27you can use what in microsoft azure to build natural language processing solutions?
azure ai language
28to build NLP solutions including speech recognition and synthesis, real-time translations, conversations transcriptions and more in azure?
azure ai speech
29this is an area of ai that deals with managing, processing, and using high volumes of variety of data found in forms and documents?
document intelligence
30azure ai document intelligence is what?
processing invoices, receipts, health insurance cards, taxes and more.
31this is used to describe solutions that involve extracting information from large volumes of often unstructured data to create searchable knowledge stores?
knowledge mining
32azure ai search is what?
an enterprise, search solution that has tools for building indexes. these indexes can be used for internal only use, or to enable searchable content on a public facing internet access
33this describes a category of capabilities within ai that create original content
generative ai
34generative ai takes natural langauge input and returns appropriate response in what format?
natural langauge, image, code, and audio and more.
35azure open ai services is what?
is Microsoft's cloud solution for deploying, customizing, and hosting generative ai models.
36you can use ______ to create generative ai solutions?
azure ai studio
37what are the 6 criteria for responsible ai?
fairness, reliability and safety, privacy and security, inclusiveness, transparancy, accountability
38what is machine learning?
the idea for this is to use data from past observations to predict unknown outcomes or values. the origin of this is from statistics and mathematical modeling of data
39a MLM includes a ______ to calculate an output value based on one or more input values
function
40the process of defining a function is known as ______
training
41after a function has been defined you can use it to predict new vales in a process called?
inferencing
42the training data consists of _____ observations
past
43__________ include the observed attribute of feature of the thing being observed and the known value of the thing you want to train a model to predict is called ____
observations, lablel
47once the training is completed the trained model can be used for ___
inferencing
48what are the type of machine learning?
supervised machine learning and unspervised machine learning
49what is the subsets of supervised machine learning?
regression and classification
50what are the components of classification machine learning?
binary and multiclass classification
51what is a general term for machine learning algorithms in which training data includes both feature values and known label values?
supervised machine learning
52supervised machine learning is also used to do what?
train models by determining a relationship between the features and labels in past observations so that the unknown labels can be predicted for features in future cases
53what is regression?
this is apart of supervised machine learning in which the label predicted by the model is a numeric value
54what is classification?
this is apart of supervised machine learning and in which the label represents a categorization or class. there are two common classifications: binary and multiclass
55what is binary classification?
in this, the label determines whether the observed item is (or isn't) an instance of a specific class. usually a true or false, positive/negative result
56what is multiclass classification?
extends binary classification to predict a label that represents one of multiple possible classes.
57this involves training models using data that consists only of feature values without any known labels.
determines the relationships between the features of the observations in the training data
unsupervised machine learning
58what is the most common form of unsupervised machine learning? this type of algorithm identifies similarities between observations based on their features and groups them into discrete ______
clustering
59these models are trained to predict numeric label values based on training data that includes both features and known labels
regression
60this is a classification like regression, is supervised machine learning technique; and therefore, follows the same integrative process of training, validating, and evaluating, numeric values like a regression model, the algorithms used to train classification modes calculate probability values for class assignments and evaluation metrics used to assess model performance the predicted classes to the actual classes.
binary classification
61this is used to predict to which of multiple possible classes on observation belongs. it follows the same iterative train, validate, and evaluate process as regression and binary classification in which a subset of the training data is held back to validate the trained models
multiclass classification