Вы находитесь на странице: 1из 21

TOPIC 1 PROBLEM

DOMAIN OF ARTIFICIAL
INTELLIGENCE
ITS662 - Intelligent Systems Development

By Zaaba Ahmad 10/30/2017


TOPIC 1
Topic Outline

1. Pattern Recognition
2. Computer Vision / Robotic
3. Planning / Decision Making
4. Intelligent Computer Aided Instruction
5. Learning Intelligent Computer Aided Design / Manufacturing

By Zaaba Ahmad 10/30/2017


AI PROBLEM DOMAIN

https://www.tutorialspoint.com/artificial_intelligence/artificial_intelligence_research_areas.htm

By Zaaba Ahmad 10/30/2017


TYPICAL PROBLEMS ADDRESSED BY
INTELLIGENT SYSTEMS

Problem type Description


Diagnosis Inferring malfunctions of an object from its behaviour and
recommending solutions.
Selection Recommending the best option from a list of possible
alternatives.
Prediction Predicting the future behaviour of an object from its
behaviour in the past.
Classification Assigning an object to one of the defined classes.
Clustering Dividing a heterogeneous group of objects into
homogeneous subgroups.
Optimisation Improving the quality of solutions until an optimal one is
found.
Control Governing the behaviour of an object to meet specified
requirements in real-time.

By Zaaba Ahmad 10/30/2017


TYPICAL PROBLEMS ADDRESSED BY
INTELLIGENT SYSTEMS
Task of Problem type Input Data Description Output Response
Classification
Diagnosis Inferring malfunctions of an object from its behaviour and
Speaker Voice
recommending solutions. Name of speaker
Recognition
Selection Recommending the best option from a list of possible
alternatives.
Weather Prediction Weather maps Weather forecast
Predicting the future behaviour of an object from its
Prediction behaviour in the past.

Medical Diagnosis
Classification Symptoms Disease
Assigning an object to one of the defined classes.
Clustering Dividing a heterogeneous group of objects into
homogeneous subgroups.
Stock Market
Optimisation
Financial news and Predicted market ups
Improving the quality of solutions until an optimal one is
Prediction charts
found. and downs.
Control Governing the behaviour of an object to meet specified
requirements in real-time.

By Zaaba Ahmad 10/30/2017


PROBLEM DOMAIN OF ARTIFICIAL
INTELLIGENCE
Pattern Recognition

Computer Vision / Robotic

Planning / Decision Making

Intelligent Computer Aided Instruction

Learning Intelligent Computer Aided Design / Manufacturing

By Zaaba Ahmad 10/30/2017


PATTERN RECOGNITION

Pattern recognition is a branch of machine learning that focuses on the


recognition of patterns and regularities in data.
Pattern recognition systems are in many cases trained from labeled "training"
data (supervised learning).
But when no labeled data are available other algorithms can be used to
discover previously unknown patterns (unsupervised learning).
Pattern recognition generally aim to provide a reasonable answer for all
possible inputs and to perform "most likely" matching of the inputs, taking into
account their statistical variation.

By Zaaba Ahmad 10/30/2017


PATTERN RECOGNITION
SYSTEM
Medical science - pattern recognition is the basis for computer-aided
diagnosis (CAD) systems. CAD describes a procedure that supports the
doctor's interpretations and findings.
Automatic speech recognition (SIRI, Google Voice, Alexa (Amazon Echo))
Classification of text into several categories (e.g., spam/non-spam email
messages, psychometric properties)
Automatic recognition of images of human faces, or handwriting image
extraction from forms.
https://quickdraw.withgoogle.com/

By Zaaba Ahmad 10/30/2017


PATTERN RECOGNITION (NEWS)
Facebook to help in suicide prevention through AI, pattern recognition -
http://www.business-standard.com/article/technology/facebook-to-help-in-
suicide-prevention-through-ai-pattern-recognition-117030200243_1.html
Researchers Claim High Accuracy in Understanding Terrorists Next Moves -
http://www.insurancejournal.com/news/national/2017/03/06/443633.htm
Quantum computer learns to see trees -
http://www.sciencemag.org/news/2017/03/quantum-computer-learns-see-
trees
Mind-Reading Computers That Can Translate Thoughts into Words -
https://www.scientificamerican.com/article/mind-reading-computers-that-
can-translate-thoughts-into-words/

By Zaaba Ahmad 10/30/2017


PROBLEM DOMAIN OF ARTIFICIAL
INTELLIGENCE
Pattern Recognition

Computer Vision / Robotic

Planning / Decision Making

Intelligent Computer Aided Instruction

Learning Intelligent Computer Aided Design / Manufacturing

By Zaaba Ahmad 10/30/2017


COMPUTER VISION / ROBOTIC

Computer vision is concerned with the automatic extraction, analysis and


understanding of useful information from a single image or a sequence of
images.
It involves the development of a theoretical and algorithmic basis to
achieve automatic visual understanding
The image data can take many forms, such as video sequences, views from
multiple cameras, or multi-dimensional data from a medical scanner.
Computer vision is an interdisciplinary field that deals with how computers
can be made for gaining high-level understanding from digital images or
videos.
From the perspective of engineering, it seeks to automate tasks that the
human visual system can do.

By Zaaba Ahmad 10/30/2017


COMPUTER VISION SUB DOMAIN

Scene Event Object


Video tracking
reconstruction detection recognition

Object pose Motion


Learning Indexing
estimation estimation

Image
restoration.

By Zaaba Ahmad 10/30/2017


COMPUTER VISION APPLICATION
Automatic inspection, e.g., in manufacturing applications;
Assisting humans in identification tasks, e.g., a species identification system;
Controlling processes, e.g., an industrial robot;
Detecting events, e.g., for visual surveillance or people counting;
Interaction, e.g., as the input to a device for computer-human interaction;
Modeling objects or environments, e.g., medical image analysis or
topographical modeling;
Navigation, e.g., by an autonomous vehicle or mobile robot; and
Organizing information, e.g., for indexing databases of images and image
sequences.
By Zaaba Ahmad 10/30/2017
COMPUTER VISION APPLICATION
One of the most prominent application fields is medical computer vision or
medical image processing.
This area is characterized by the extraction of information from image data
for the purpose of making a medical diagnosis of a patient.
Generally, image data is in the form of microscopy images, X-ray images,
angiography images, ultrasonic images, and tomography images.
An example of information which can be extracted from such image data is
detection of tumours, arteriosclerosis or other malign changes.

By Zaaba Ahmad 10/30/2017


By Zaaba Ahmad
Image acquisition

Pre-processing

Feature extraction

Detection/segmentation

High-level processing

Decision making
PROCESS FLOW
COMPUTER VISION FUNCTION

10/30/2017
PROBLEM DOMAIN OF ARTIFICIAL
INTELLIGENCE
Pattern Recognition

Computer Vision / Robotic

Planning / Decision Making

Intelligent Computer Aided Instruction

Learning Intelligent Computer Aided Design / Manufacturing

By Zaaba Ahmad 10/30/2017


PLANNING / DECISION MAKING /
SCHEDULING
Concerns with the realization of strategies or action sequences, typically for
execution by intelligent agents, autonomous robots and unmanned vehicles.
Unlike classical control and classification problems, the solutions are complex
and must be discovered and optimized in multidimensional space.
Solutions can be found and evaluated prior to execution.
Models and policies must be adapted. Solutions usually resort to iterative trial
and error processes.
These include dynamic programming, reinforcement learning and
combinatorial optimization. Languages used to describe planning and
scheduling are often called action languages.

By Zaaba Ahmad 10/30/2017


CLASSICAL PLANNING PROBLEM

which can
a unique
durationless deterministic be taken and a single
known initial
actions, actions, only one at agent.
state,
a time,

By Zaaba Ahmad 10/30/2017


PLANNING / DECISION MAKING
Classical planning
forward chaining state space search, possibly enhanced with heuristics,
backward chaining search, possibly enhanced by the use of state constraints (see STRIPS,
graphplan),
Reduction to other problems
reduction to the propositional satisfiability problem (satplan).
reduction to Model checking - both are essentially problems of traversing state spaces, and the
classical planning problem corresponds to a subclass of model checking problems.
Temporal planning
Temporally overlapping actions with a duration being taken concurrently, that the definition of a
state has to include information about the current absolute time and how far the execution of each
active action has proceeded.
Probabilistic planning
Main articles: Markov decision process and Partially observable Markov decision process
Probabilistic planning can be solved with iterative methods such as value iteration and policy
iteration, when the state space is sufficiently small. With partial observability, probabilistic planning is
similarly solved with iterative methods, but using a representation of the value functions defined for
the space of beliefs instead of states.
By Zaaba Ahmad 10/30/2017
PROBLEM DOMAIN OF ARTIFICIAL
INTELLIGENCE
Pattern Recognition

Computer Vision / Robotic

Planning / Decision Making

Intelligent Computer Aided Instruction

Learning Intelligent Computer Aided Design / Manufacturing

By Zaaba Ahmad 10/30/2017


By Zaaba Ahmad 10/30/2017

Вам также может понравиться