About
What is Artificial Intelligence(AI)? , Evolution , Applications of AI? , Features of AI , What is Intelligence and its types?,
What are Agents and Environment? , Fear of AI , Machine Learning , Difference between AI, ML and Deep Learning ,
Applications of ML , Algorithms of AL and ML , Future of AI
1. ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
Dr.M.Inbavalli
Vice Principal
Marudhar Kesari Jain College for Women
Vaniyambadi-635751
1
2. Overview
• What is Artificial Intelligence(AI)?
• Evolution
• Applications of AI?
• Features of AI
• What is Intelligence and its types?
• What are Agents and Environment?
• Fear of AI
• Machine Learning
• Difference between AI, ML and Deep Learning
• Applications of ML
• Algorithms of AL and ML
• Future of AI
2
3. • Artificial Intelligence
• Ability for a machine to perform tasks that would normally human do.
• artificial intelligence is making machines "intelligent“ - acting as we
would expect people to act.
• Capability of machine to imitate intelligent human behavior-Merriam
Webster.
• The inability to distinguish computer responses from human responses
is called the Turing test.
• Intelligence requires knowledge .
3
3
5. • Artificial Intelligence
• From a business perspective AI is a set of very powerful tools, and
methodologies for using those tools to solve business problems.
• From a programming perspective, AI includes the study of symbolic
programming, problem solving, and search.
• Typically AI programs focus on symbols rather than numeric processing.
or Problem solving - achieve goals.
• Search - seldom access a solution directly. Search may include a variety of
techniques.
• include:
• – LISP, developed in the 1950s
• LISP is a functional programming language with procedural extensions
5
5
9. S.
No
Programming
Languages
Features
1
LISP
developed in 1950s
A functional programming language with procedural extensions
specifically designed for processing heterogeneous lists -- typically a list of symbols.
Features of LISP
are run- time type checking,
recursion, dynamic typing, Automatic storage management, High-order functions, self-hosting
compiler, and tree data structure.
2 PROLOG developed in 1970s
Prolog is a rule-based and declarative language containing facts and rules
based on first order logic,Features- pre-designed search mechanism, recursive nature,
abstraction, non determinism, backtracking mechanism, and pattern matching.
3 Object-
oriented
languages -
Smalltalk,
Objective C,
C++
Object oriented extensions to LISP (CLOS - Common LISP Object System) and PROLOG (L&O -
Logic & Objects) are also used.
9
AI programming languages
9
13. • Applications of AI
• Game Playing- video games
• Speech Recognition
• Understanding Natural Languages
• Image Recognition
• Automated customer support-Sending reminders, notifications, timing
alerts, messages, currencies to Rs. Conversion
• Health care-accuracy in diagnosing
• Finance- accuracy in decision-stock market
• Smart cars and drones
• Travel and navigation-book Trips/google maps
13
14. • Applications of AI
• Social Media
• Smart home
• Creative arts/Animations
• Security and Survillenace
• Uber
• Loan and Credit card processing
• Online banking
• Spam filters
• Identification Technologies-Biometric
• Intrusion Detection
• Agriculture
14
15. • Applications of AI
• Customer Preferences - based on previous searches Eg.Netflix
• Chat boxes-NLP, virtual assistant google duplex
• Space Exploration-Kepler telescope in order to identify a distant eight-
planet solar system.
15
18. • Artificial Intelligence Subfields - AI is EVERYWHERE –
• Machine Translation
• - Google Translate
• - Spam Filters
• Digital Personal Assistants
• - Siri
- Google Assistant
• - Cortana
• - Alexa
18
19. • Artificial Intelligence Subfields - AI is EVERYWHERE
• - Game players
• - DeepBlue
• - AlphaGo
• - “The Computer” in video games
• - Speech Recognition Systems
• - IBM
• - Dragon
• - Image Recognitions Systems
• - AlgorithmicTrading Systems
• - Black-Scholes Model (Caused crash in 1987)
• - AutomatedTrading Services
• - Recommender Systems
• - Amazon’s Suggestions
• - Google Ads
19
23. • What is Intelligence?
• ability of a system to calculate, reason, perceive relationships and
analogies, learn from experience, store and retrieve information from
memory, solve problems, comprehend complex ideas, use natural
language fluently, classify, generalize, and adapt new situations
• Types of Intelligence
23
24. Intelligence Description Example
Linguistic intelligence
The ability to speak, recognize, and
use mechanisms of phonology
(speech sounds), syntax
(grammar), and semantics
(meaning).
Narrators, Orators
Musical intelligence
The ability to create, communicate
with, and understand meanings
made of sound, understanding of
pitch, rhythm.
Musicians, Singers, Composers
Logical-mathematical intelligence
The ability of use and understand
relationships in the absence of
action or objects. Understanding
complex and abstract ideas.
Mathematicians, Scientists
Spatial intelligence
The ability to perceive visual or
spatial information, change it, and
re-create visual images without
reference to the objects, construct
3D images, and to move and rotate
them.
Map readers, Astronauts, Physicists
24
25. Intelligence Description Example
Bodily-Kinesthetic intelligence
The ability to use complete or part
of the body to solve problems or
fashion products, control over fine
and coarse motor skills, and
manipulate the objects.
Players, Dancers
Intra-personal intelligence
The ability to distinguish among
one’s own feelings, intentions, and
motivations. Gautam Buddhha
Interpersonal intelligence
The ability to recognize and make
distinctions among other people’s
feelings, beliefs, and intentions. Mass Communicators, Interviewers
25
27. • Intelligence
• Reasoning − It is the set of processes that enables us to provide basis for
judgement, making decisions, and prediction.
• Inductive Reasoning-specific observations to makes broad general statements
• Example − "Nita is a teacher. Nita is studious. Therefore, All teachers are studious."
• Deductive Reasoning-It starts with a general statement and examines the
possibilities to reach a specific, logical conclusion.
• Example − "All women of age above 60 years are grandmothers. Shalini is 65 years. Therefore,
Shalini is a grandmother.“
Learning-gaining knowledge or skill by studying, practising, being
taught, or experiencing something.
Types-Auditory,stimulus,perceptutional, observational etc
Problem Solving -Decision making
Perception-sensor
Linguistic – Ability to speak,listen,write
27
29. • Types of Learning Based on Ability
• Artificial Narrow Intelligence-does not posses any thinking ability.
Eg.-Siri, Alexa, Self-driving cars, Alpha-Go, Sophia the humanoid and so on
• Artificial General Intelligence-ability to think and make decisions
• Eg-Biological , agricultural, drowns , scientific etc
• Artificial Super Intelligence-super pass humans
• Eg.film, fictions
• Types of Learning Based on Functionality
• Reactive Intelligence- operate solely based on the present data, taking into
account only the current situation
• cannot form inferences from the data to evaluate their future actions.
• perform a narrowed range of pre-defined tasks.Eg. IBM Chess program
29
30. • Limited Memory AI
• used to store past experiences and hence evaluate future actions.
Eg.Self Driving car-use sensor for decision
• Theory of Mind AI
• major role in psychology
• emotional intelligence so that human believes and thoughts can be
better comprehended.
• Self Aware
• own consciousness and become self-aware.
• Superintelligence
• Futuristics
30
31. • Branches of AI
• Logical AI-mathematical logical language, do by inferring
• Search —large numbers of possibilities Eg.chess
• Pattern Recognition-try to match a pattern of eyes and a nose in a scene in
order to find a face. Eg.Fraud detection
• Representation-Visuals using logics
• Inference-Mathematical logical deduction Eg. when we hear of a bird, we infer
that it can fly, monotonic
• Common sense knowledge and Reasoning- futuristic
• Learning from experience-types of learning
• Planning – scheduling , drawings
• Ontology-Deals with objects and its properties
• Heuristic-search or to measure how far a node in a search tree
• Genetic-Hierarchial and high level problem solving
31
32. • Difference between Humans and Machines
S.No Humans Machines
1 Perceive by patterns perceive by set of rules and data.
2 store and recall information by
patterns
Eg:40404040
searching algorithms
3 figure out the complete object even if
some part of it is missing
machines cannot do
32
33. Task Domains of Artificial Intelligence
Mundane (Ordinary) Tasks Formal Tasks Expert Tasks
•Perception
• Computer Vision
• Speech, Voice
•Mathematics
•Geometry
•Logic
•Integration and Differentiation
•Engineering
•Fault Finding
•Manufacturing
•Monitoring
•Natural Language Processing
• Understanding
• Language Generation
• Language Translation
•GamesGo
•Chess (Deep Blue)
•Ckeckers
Scientific Analysis
Common Sense Verification Financial Analysis
Reasoning Theorem Proving Medical Diagnosis
Planing Creativity
•Robotics
• Locomotive
33
35. • What are Agent and Environment?
• Artificial intelligence is defined as a study of rational agents A rational agent
could be anything which makes decisions, as a person, firm, machine, or software.
It carries out an action with the best outcome after considering past and current
percepts
• Human Agent, Robotic agent, Software Agent
35
36. • An AI system is composed of an agent and its environment. The agents act in
their environment. The environment may contain other agents. An agent is
anything that can be viewed as :
• perceiving its environment through sensors and
• acting upon that environment through actuators
• Agent Terminology
• Performance Measure of Agent
• Behavior of Agent
• Percept –perceptual instance at a given instance
• Percept Sequence-perceived till date
• Agent Function-map from percept sequence to an action
36
37. • Exampes:AI assistants, like Alexa and Siri,
• they use sensors to perceive a request made by the user and the
automatically collect data from the internet without the user's help. They
can be used to gather information about its perceived environment such
as weather and time.
37
38. • Examples of Agent:-
A software agent has Keystrokes, file contents, received network packages which act
as sensors and displays on the screen, files, sent network packets acting as actuators.
A Human agent has eyes, ears, and other organs which act as sensors and hands,
legs, mouth, and other body parts acting as actuators.
A Robotic agent has Cameras and infrared range finders which act as sensors and
various motors acting as actuators.
• Types of Agents
• Simple Reflex Agents
• Model-Based Reflex Agents
• Goal-Based Agents
• Utility-Based Agents
• Learning
38
39. • Fear Over AI
• - a good example rajini enthiran movie
• AI will produce biased outcomes
• Algorithms are only as good as the data that they are trained on. So if a dataset
includes the historical biases of an organization, then the predictions it makes will
reflect that historical behavior.– ignore expert who belong to other behaviour
• We (will) have no idea why AI does what it does-black box
• Fear of unforseen - automatic vehicle driving
• AI is a Job killer
• Bad people do bad things
• Privacy Considerations-Automatic recording
• Lacking out of box thinking
39
41. • Machine Learning
• Machine learning is concerned with algorithms which train a machine
learning model to learn how to perform tasks using data rather than
hand-coded rules.
• Machine learning data most frequently takes the form of input-label pairs
(x, y) where x is the input to a machine learning model and y is the label
or expected output
• Data is often split into three partitions: training data,
validation/development data, and testing data
41
41
42. Artificial Intelligence Machine learning
Artificial intelligence is a technology which enables a
machine to simulate human behavior.
Machine learning is a subset of AI which allows a
machine to automatically learn from past data without
programming explicitly.
The goal of AI is to make a smart computer system like
humans to solve complex problems.
The goal of ML is to allow machines to learn from data so
that they can give accurate output.
In AI, we make intelligent systems to perform any task
like a human.
In ML, we teach machines with data to perform a
particular task and give an accurate result.
Machine learning and deep learning are the two main
subsets of AI.
Deep learning is a main subset of machine learning.
AI has a very wide range of scope. Machine learning has a limited scope.
AI is working to create an intelligent system which can
perform various complex tasks.
Machine learning is working to create machines that can
perform only those specific tasks for which they are
trained.
AI system is concerned about maximizing the chances of
success.
Machine learning is mainly concerned about accuracy
and patterns.
42
42
43. Artificial Intelligence Machine learning
The main applications of AI are Siri, customer support
using catboats, Expert System, Online game playing,
intelligent humanoid robot, etc.
The main applications of machine learning are Online
recommender system, Google search
algorithms, Facebook auto friend tagging
suggestions, etc.
On the basis of capabilities, AI can be divided into three
types, which are, Weak AI, General AI, and Strong AI.
Machine learning can also be divided into mainly three
types that are Supervised learning, Unsupervised
learning, and Reinforcement learning.
It includes learning, reasoning, and self-correction. It includes learning and self-correction when introduced
with new data.
AI completely deals with Structured, semi-structured,
and unstructured data.
Machine learning deals with Structured and semi-
structured data.
43
43
45. Learning Proceeding Cont.
7/22/2020 45
Machine Learning is a type of Artificial
Intelligence that provides computers with the
ability to learn without being explicitly
programmed
AI
M
L
DL Part of the machine learning field of learning representations of data.
Exceptional effective at learning
Utilizes learning algorithms that derive meaning out of data by using a hierarchy of
multiple layers that mimic the neural networks of our brain
If the system is provided with tons of information, it begins to understand it and
respond in useful ways
45
49. • Searching is the universal technique of problem solving
• Popular AI Search Algorithms
• Single Agent Pathfinding Problems
• Travelling Salesman Problem, Rubik’s Cube, and Theorem Proving.
49
49
50. • Search Terminology
• Problem Space − It is the environment in which the search takes place. (A set
of states and set of operators to change those states)
• Problem Instance − It is Initial state + Goal state.
• Problem Space Graph − It represents problem state. States are shown by
nodes and operators are shown by edges.
• Depth of a problem − Length of a shortest path or shortest sequence of
operators from Initial State to goal state.
• Space Complexity − The maximum number of nodes that are stored in
memory.
• Time Complexity − The maximum number of nodes that are created.
• Admissibility − A property of an algorithm to always find an optimal
solution.
• Branching Factor − The average number of child nodes in the problem space
graph.
• Depth − Length of the shortest path from initial state to goal state.
50
50
54. • THE FUTURE OF ARTIFICIAL INTELLIGENCE
• Artificial intelligence is impacting the future of virtually every industry
and every human being. Artificial intelligence has acted as the main
driver of emerging technologies like big data, robotics and IoT, and it
will continue to act as a technological innovator for the foreseeable
future.
54
54
But what is Artificial Intelligence. In general, it is the ability for a machine to perform tasks that would normally require a person to do. And just like people, it’s the ability to take information, make decisions based on it and cause an action to be taken. Such as moving an arm, creating and image or text, or providing a suggestion.