Unit 1: Introduction to AI on Azure Department Of BCA

Introduction to AI on Azure

1. Define/What is AI.
Artificial intelligence (AI) is the creation of software that imitates human behaviour and
capabilities.
Key elements include:
• Machine learning
• Anomaly detection
• Computer Vision
• Natural language processing
• Conversational AI

2. Define/what Azure AI.

Azure AI is a portfolio of AI services designed for developers and data scientists.

3. Define computer Vision.

Computer vision is the area of AI that deals with visual processing. It is a service which
enables software engineers to create intelligent solutions that extract information from
images.

4. Define Natural Language Processing.

Natural Language Processing (NLP) is the area of AI that deals with creating software
that understands written and spoken language.

5. Define Knowledge Mining.

It is the capability to extract information from large volumes of unstructured data to
create a knowledge store.

6. Define conversational AI.

The capability of a software "agent" to participate in a conversation.

7. What are the Applications of AI.

• AI in Healthcare : Healthcare Industries are applying AI to make a better and
faster diagnosis than humans. AI can help doctors with diagnoses and can inform
when patients are worsening so that medical help can reach to the patient before
hospitalization.
Unit 1: Introduction to AI on Azure Department Of BCA

• AI in Robotics: with the help of AI, we can create intelligent robots which can
perform tasks with their own experiences without pre-programmed. Humanoid
Robots are best examples for AI in robotics, Erica and Sophia .

• AI in Gaming: AI can be used for gaming purpose. The AI machines can play
strategic games like chess, where the machine needs to think of a large number of
possible places.
• AI in education: AI can automate grading so that the tutor can have more time to
teach. AI chatbot can communicate with students as a teaching assistant.

• AI in Entertainment: We are currently using some AI based applications in our

daily life with some entertainment services such as Netflix or Amazon. With the
help of ML/AI algorithms, these services show the recommendations for
programs or shows.
• AI in Travel and Transport: AI is capable of doing various travel related works
such as from making travel arrangement to suggesting the hotels, flights, and best
routes to the customers. Travel industries are using AI-powered chatbots which
can make human-like interaction with customers for better and fast response.

8. What are the Azure machine learning features and capabilities?

Features and its capabilities:
• Automated machine learning: This feature enables non-experts to quickly create
an effective machine learning model from data.

• Azure Machine Learning designer: A graphical interface enabling no-code

development of machine learning solutions.

• Data and compute management: Cloud-based data storage and compute

services that professional data scientists can use.

• Pipelines: Data scientists, software engineers and IT operations professionals can

define pipelines.

9. Explain Computer vision tasks.

Task1: Image Classification: It involves training a machine learning model to classify
images based on their contents.
Example: In traffic monitoring solution we use image classification model to classify
images based on type of vehicle such as taxis, buses and cyclists.

Task2: Object detection: These machine learning models are trained to classify
individual objects within an image, and identify their location with a bounding box.
Unit 1: Introduction to AI on Azure Department Of BCA

Example, a traffic monitoring solution might use object detection to identify the
location of different classes of vehicle.

Task3: Semantic Segmentation: It is a machine learning technique in which individual

pixels in the image are classified according to the object.
Example: A traffic monitoring solution might overlay traffic images with mask layers to
highlight different vehicles.

Task 4: Image Analysis: create solutions that combine machine learning models with
advanced image analysis techniques to extract information from images.

Task 5: Face Detection, Analysis and Recognition: It is a specialized form of object

detection that locates human faces in an image.
It can be combined with classification and facial geometry analysis to recognise
individuals.

Task 6: Optical Character Recognition(OCR): It is a technique used to detect and read

text in image.
You can use OCR to read text in paragraphs or to extract information from scanned
documents.

10. List and explain Computer vision service and capabilities or cognitive
services azure provides.
Services and Capabilities:
• Computer vision: Use this service to analyze images and video and extract
description tags.
• Custom Vision: Use this service to train image classification and object detection
model.
• Face: It enables you to build face detection and facial recognition solutions.
• Form Recogniser: Use this service to extract information from scanned forms
and invoices.

11. What are NLP services in Microsoft Azure?

• Text Analytics: Use this service to analyze text documents and extract key
phrases, detect entities (such as places, dates, and people), and evaluate sentiment
(how positive or negative a document is).
• Translator Text: Use this service to translate text between more than 60
languages.
• Speech: Use this service to recognize and synthesize speech, and to translate
spoken languages.
Unit 1: Introduction to AI on Azure Department Of BCA

• Language Understanding Intelligent Service (LUIS): Use this service to train a

language model that can understand spoken or text-based commands.

12. Explain the steps to configure Tune Model Hyper parameters.

• Add the Tune model Hyper parameters component to your pipeline in the designer.
• Connect an untrained model to the leftmost input.
• Add the dataset that you want to use for training and connect it to the middle input of
Tune Model Hyper parameters.
• In the right panel of tune model hyper parameters ,choose a value for parameter sweeping
mode ,It controls how parameters are selected.
o Entire grid: It is useful when you don’t know what the best parameter settings
might be is.
o Random sweep: The component will randomly select parameter values over a
system-defined range.
• For Label Column selector to choose a single label column.
• Choose the number of runs:
o Maximum number of runs on random sweep: If you choose a random sweep ,you
can specify how many times the model should be trained.
• For, Ranking choose a single metric to use for ranking the models.
• For Random seed, enter an integer number as a pseudo random number generator state
used for randomly selecting parameter values over a pre-defined range.
• Submit the pipeline.

13. Define neural network.

The basic unit of the brain is known as neuron. When a large number of neurons are
present together to give out a large number of outputs it forms a neural layer. These
multiple layers combine to form a neural network.

14. Explain Artificial Intelligence Workloads

There are basic 6 AI Workloads
1. Predicting and Forecasting: It can have a large scale of impact in our current day
world with power of accuracy it holds.
Example: Weather forecasting systems: AI model will be provided an abundant
amount of data of weather conditions to predict weather changes and long term
climate impact.
2. Anomaly Detection: It is using machines to observe and find the unexpected value,
within an already established range of values. Example: Smart Watches
3. Computer Vision: It analyzes videos and images to extract specific information. The
information may be images, video or subject of matter in an image.
Unit 1: Introduction to AI on Azure Department Of BCA

It involves a model being trained with thousand of pictures labels videos and key
contents to be able to recognize and classify images. Example : Every time safe
search is run when surfing on google.
4. Natural Language Processing(NLP):It is a tool for machines to be able to
communicate in human languages as well as convert speech to text and vice versa.
It allows computers to understand questions, requests and commands as well as
respond to them.
Example:Siri
5. Knowledge Mining: It is process where computers and machines extract specific
valuable data from unstructured files or ontent.
There are three basic steps:
Step1: Pull the data simple process of pulling out the specified data.
Step2:Use the appropriate cognitive service to extract value from gathered data.
Step3: analysis of data through exploration.
6. Conversational AI: It allows simple AI solutions to be able to converse and talk with
humans.
Chatbots: can be used for things like customer support, making appointments.

15. Is there any service for Anomaly detection from Microsoft Azure?
The Anomaly Detector service provides an application programming interface (API)
that developers can use to create anomaly detection solutions.

16. What are the Conversational AI services in Microsoft Azure?

• QnA Maker: This cognitive service enables you to quickly build a knowledge
base of questions and answers that can form the basis of a dialog between a
human and an AI agent
• Azure Bot Service: This service provides a platform for creating, publishing, and
managing bots. Developers can use the Bot Framework to create a bot and
manage it withAzure Bot Service - integrating back-end services like QnA
Maker and LUIS, and connecting to channels for web chat, email, Microsoft
Teams, and others.

17. What is responsible AI?

Artificial Intelligence is a powerful tool that can be used to greatly benefit the world.
However, like any tool, it must be used responsibly. At Microsoft, AI software
development is guided by a set of six principles, designed to ensure that AI applications
provide amazing solutions to difficult problems without any unintended negative
consequences.

18. What are the six guiding principles of responsible AI?

Unit 1: Introduction to AI on Azure Department Of BCA

• Fairness: AI systems should treat all people fairly. For example, suppose you
create a machine learning model to support a loan approval application for a bank.
The model should make predictions of whether or not the loan should be
approved without incorporating any bias based on gender, ethnicity, or other
factors that might result in an unfair advantage or disadvantage to specific groups
of applicants.
• Reliability and safety: AI systems should perform reliably and safely. For
example, consider an AI-based software system for an autonomous vehicle; or a
machine learning model that diagnoses patient symptoms and recommends
prescriptions. Unreliability in these kinds of system can result in substantial risk
to human life.
• Privacy and security: AI systems should be secure and respect privacy. The
machine learning models on which AI systems are based rely on large volumes of
data, which may contain personal details that must be kept private. Even after the
models are trained and the system is in production, it uses new data to make
predictions or take action that may be subject to privacy or security concerns.
• Inclusiveness: AI systems should empower everyone and engage people.AI
should bring benefits to all parts of society, regardless of physical ability, gender,
sexual orientation, ethnicity, or other factors.
• Transparency: AI systems should be understandable. Users should be made fully
aware of the purpose of the system, how it works, and what limitations may be
expected.
• Accountability: People should be accountable for AI systems. Designers and
developers of AI-based solution should work within a framework of governance
and organizational principles that ensure the solution meets ethical and legal
standards that are clearly defined.

19. You want to train a model that classifies images of dogs and cats based on a
collection of your own digital photographs. Which Azure service should you
use?
Computer Vision

20. What is machine Learning

This is often the foundation for an AI system, and is the way we "teach" a computer
model to make prediction and draw conclusions from data.
Machine learning is a technique that uses mathematics and statistics to create a model
that can predict unknown values
Unit 1: Introduction to AI on Azure Department Of BCA

21. What are the various kinds of machine learning model types?
• Regression (supervised machine learning): We use historic data to train the
model to predict the numerical value.
• Classification (supervised machine learning): We can fit the features into the
model and predict the classification of the label
• Unsupervised Machine learning: You don't have a label to predict. You only
have features. You have to create clusters based on the features.

22. What is the process of machine learning regardless of the model? OR

Principles of Machine Learning model on Azure.
• Data Ingestion: You need to get the data to train your model.
• Data Pre-processing: Identify the features that helps the model to predict and
discarding others
• Data Cleaning: Fix any errors or removing the items which has errors.
• Replacing Feature Values: Find the replacement feature values if any missing. In
this process you might use existing feature engineering to find the value
• Apply Algorithms: Apply algorithms on this data for the processing until you are
happy with the model predictions.
• Deploy Model: Finally you deploy your model into machine learning service so
that applications can connect to it.

23. Mention the applications of Machine Learning.

• Image recognition: It is one of the most common applications of machine learning. It is
used to identify objects, persons, places, digital images,

• Speech Recognition: While using Google, we get an option of "Search by voice," it

comes under speech recognition, and it's a popular application of machine learning.
• Traffic prediction: If we want to visit a new place, we take help of Google Maps, which
shows us the correct path with the shortest route and predicts the traffic conditions.
• Self-driving cars: One of the most exciting applications of machine learning is self-
driving cars. Machine learning plays a significant role in self-driving cars. Tesla, the most
popular car manufacturing company is working on self-driving car
• Medical Diagnosis: In medical science, machine learning is used for diseases diagnoses.
With this, medical technology is growing very fast and able to build 3D models that can
predict the exact position of lesions in the brain. It helps in finding brain tumors and other
brain-related diseases easily.
Unit 1: Introduction to AI on Azure Department Of BCA

24. Mention the features of NLP workloads on Azure

The features of NLP on Azure
• Sentiment Analysis
• Topic detection
• Language detection key phrase extraction
• document categorization.

25. What can Computer Vision cognitive service do? OR

Mention the features of computer vision workloads on Azure
• Suggest relevant tags that could be used to index an image.
• Categorize an image
.• Identify objects in an image.
• Detect faces and people in an image.
• Recognize celebrities and landmarks in an image.
• Read text in an image.

26. When using Computer Vision, what is the difference between Computer
Vision and Cognitive Services?
Computer Vision: A specific resource for the Computer Vision service. Use this
resource type if you don’t intend to use any other cognitive services, or if you want to
track utilization and costs for your Computer Vision resource separately.

Cognitive Services: A general cognitive services resource that includes Computer Vision
along with many other cognitive services; such as Text Analytics, Translator Text, and
others. Use this resource type if you plan to use multiple cognitive services and want to
simplify administration and development.

27. Explain the Considerations in AI.

Legal and Ethical Consideration: The legal and ethical issues that confront society
include privacy and surveillance, bias or discrimination and the role of human
judgement.Yet there are no well defined regulations in place to address the legal and
ethical issues that may rise due to use of AI in healthcare.
AI on Health research:The electronic health records (EHR) is an important field of AI.
Records in HER can be used for scientific study,quality improvement and clinical care
optimization.
AI in Drug Development: AI can be used in drug discovery and development process to
speed up and make it more cost effective and efficient,
Ethical Challenges: Ethical issues to be addressed are:
• Informed consent to use data
Unit 1: Introduction to AI on Azure Department Of BCA

• Safety and transparency

• Algorithmic fairness and biases
• Data privacy

28. What is Text Analytics?

Text analytics is a process where an artificial intelligence (AI) algorithm, running on a
computer, evaluates these same attributes in text, to determine specific insights.

29. What is Speech recognition?

The ability to detect and interpret spoken input. Speech recognition is concerned with
taking the spoken word and converting it into data that can be processed - often by
transcribing it into a text representation. The spoken words can be in the form of a
recorded voice in an audio file, or live audio from a microphone.

30. What is Speech synthesis?

The ability to generate spoken output. Speech synthesis is in many respects the reverse of
speech recognition. It is concerned with vocalizing data, usually by converting text to
speech

31. What are the services for speech recognition and speech synthesis from
Azure?
The Speech-to-TextAPI
The Text-to-Speech API