Artificial Intelligence and Mathematics

1,378 views
1,240 views

Published on

A presentation on artificial intelligence and the applications of mathematics in artificial intelligence

Published in: Education, Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
1,378
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
42
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide
  • FINANCE =Banks use artificial intelligence systems to organize operations, invest in stocks, and manage properties.HEAVY INDUSTRY =Robots have become common in many industries. They are often given jobs that are considered dangerous to humans.ONLINE=Artificial intelligence is implemented in automated online assistants that can be seen as avatars on web pages. Similar techniques may be used in answering machines of call centres, such as speech recognition software to allow computers to handle first level of customer support, text mining and natural language processing to allow better customer handling, agent training by automatic mining of best practices from past interactions, support automation and many other technologies to improve agent productivity and customer satisfaction.[8]GAMES=Games use ai and gathers result as per the decision made on spot.For example the basic ai is used in pac man . red enemy chases Pac-Man, and the pink and blue enemies try to position themselves in front of Pac-Man's mouth.[27] Although he claimed that the orange enemy's behavior is randomMEDICAL=Artificial neural networks are used as clinical decision support systems for medical diagnosis, such as in Concept Processing technology in EMR software.Other tasks in medicine that can potentially be performed by artificial intelligence include:Computer-aided interpretation of medical images. Such systems help scan digital images, e.g. from computed tomography, for typical appearances and to highlight conspicuous sections, such as possible diseases. A typical application is the detection of a tumor.Heart sound analysis[5]
  • FATHER OF ROBOTICSHIS THREE LAWS IS THE FOUNDATION OF ROBOTICS AND ARTIFICIAL INTELLIGENCE
  • Disadvantage is that it needs different variables for each time.For eg as talked before in pac man there are 255 level for a player,representing 2^8 but however at 266 th level this is what happens…………..So we go for predicate calculus another developed part of boolean theory
  • MENTION THE DEFINITION IS TOO BIG
  • For example, in a neural network for handwriting recognition, a set of input neurons may be activated by the pixels of an input image representing a letter or digit. The activations of these neurons are then passed on, weighted and transformed by some function determined by the network's designer, to other neurons, etc., until finally an output neuron is activated that determines which character was read.
  • Artificial Intelligence and Mathematics

    1. 1. ARTIFICIAL INTELLIGENCE • Computers or intelligence system with the ability to mimic or duplicate the functions of the human brain. OR • Artificial intelligence is technology and a branch of computer science that studies and develops intelligent machines and software
    2. 2. + 11/15/2013
    3. 3. • John McCarthy was an American computer scientist and cognitive scientist. • He coined the term "artificial intelligence" (AI), developed the LISP PROGRAMMING language family. • Significantly influenced the design of the ALGOL PROGRAMMING LANGUAGE, popularized timesharing, and was very influential in the early development of AI.
    4. 4. • Alan Turing was a British scientist known for his Computer , Algorithm and the very famous TURING TEST. • He had worked for the British army during World War 2 in the code ciphering section and had successfully cracked many German codes. • Turing test • The Turing test is a test of a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a 11/15/2013
    5. 5. 11/15/2013
    6. 6. • A human judge engages in natural language conversations with a human and a machine designed to generate performance indistinguishable from that of a human being. • All participants are separated from one another. If the judge cannot reliably tell the machine from the human, the machine is said to have passed the test. • The test does not check the ability to give the correct answer to questions; it checks how closely the answer resembles typical human answers. 11/15/2013
    7. 7. • The conversation is limited to a text-only channel such as a computer keyboard and screen so that the result is not dependent on the machine's ability to render words into audio. • “Can machines think?” 11/15/2013
    8. 8. • 1943 - McCulloch and Pits -- modeling neurons using on/off devices. 1950's - Claude Shannon and Alan Turing try to write chess playing programs. 1956 - John McCarthy thinks of the name "Artificial Intelligence". 1960's - Logic Theorist, GPS, microworlds, and neural networks. 1971 - NP-Completeness theory (Cook and Karp) casts doubt on general applicability of AI methods. 1970's - Knowledge based systems and expert systems. 1980's - AI techniques in widespread use, neural networks rediscovered. 1990's - Deep Blue wins against world chess champion. Image and Speech recognition becomes 11/15/2013 practical.
    9. 9. Perceptive system A system that approximates the way a human sees, hears, and feels objects Vision system Capture, store, and manipulate visual images and pictures Robotics Mechanical and computer devices that perform tedious tasks with high precision Expert system Stores knowledge and makes 11/15/2013 inferences
    10. 10. Learning system Computer changes how it functions or reacts to situations based on feedback Natural language processing Computers understand and react to statements and commands made in a “natural” language, such as English Neural network Computer system that can act like or simulate the functioning of the human brain 11/15/2013
    11. 11. 11/15/2013
    12. 12. 11/15/2013
    13. 13. 11/15/2013
    14. 14. 11/15/2013
    15. 15. • Mathematics and articial intelligence (AI) have had a symbiotic relationship. • It began when Allen Turing dreamed of taking Hilbert's tenth problem into the realm of computation that would blur the distinction between human and machine reasoning.
    16. 16. • Find an algorithm to determine whether a given polynomial Diophantine equation{a Diophantine equation is a polynomial equation that allows two or more variables to take integer values only} with integer coefficients has an integer solution. • Resolved. Result: impossible, Matiyasevich's theorem implies that there is no such algorithm. 11/15/2013
    17. 17. 11/15/2013
    18. 18. • Boolean algebra {Propositional Logic} is the subarea of algebra in which the values of the variables are the truth values true and false, usually denoted 1 and 0 respectively. • Instead of elementary algebra where the values of the variables are numbers, and the main operations are addition and multiplication, the main operations of Boolean algebra are the conjunction and, denoted ∧, the disjunction or, denoted ∨, and 11/15/2013
    19. 19. 11/15/2013
    20. 20. 11/15/2013
    21. 21. • Graph theory is the study of graphs, which are mathematical structures used to model pairwise relations between objects. • Graphs are used to represent networks of communication, data organization, computational devices, the flow of computation. 11/15/2013
    22. 22. 11/15/2013
    23. 23. • Eigenvector is an advanced level of 3D geometry and it is used in artificial intelligence to detect motion and deduce expression . • A square matrix is multiplied with the vector or the axis and this results in a change and hence can detect or simulate the same • The eigenvalues are used to determine the natural frequencies (or eigenfrequencies) of vibration, and the eigenvectors determine the shapes of these vibrational modes and hence can determine motion 11/15/2013
    24. 24. 11/15/2013
    25. 25.  Statistics is the study of the collection, organization, analysis, interpretation and presentation of data.  Created complex models such as nonlinear models as well as the creation of new types, such as generalized linear models and multilevel models and uses the most significant answer from the results to take a decision .  A large number of both general and special purpose statistical software are now available. 11/15/2013
    26. 26. 11/15/2013
    27. 27.  OPTIMIZATION THEORY is the selection of the best answer and can also be called a mix of probability and statistics.  An optimization problem consists of maximizing or minimizing a real function by systematically choosing input values from within an allowed set and computing the value of the function.  Optimization includes finding "best available" values of some objective function given a defined domain, including a variety of different types of objective functions. 11/15/2013
    28. 28. 11/15/2013
    29. 29. 11/15/2013
    30. 30. ALGORITHMIC THEORY is a subfield of information theory and computer science that concerns itself with the relationship between computation and information. Algorithmic information theory principally studies complexity measures on strings (or other data structures). 11/15/2013
    31. 31. 11/15/2013
    32. 32. LINEAR SYSTEM OF EQUATION is a collection of linear equations involving the same set of variables.  It helps in the location of the point {solution} and can estimate the location graphically.  it helps in computer simulation.  It can also determine the Solution region. 11/15/2013
    33. 33. 11/15/2013
    34. 34. CONVEX OPTIMIZATION THEORY is used in the adaptation of a robot. It takes a more probability in learning approaches.  It permits fast prototyping of learning algorithms without the need for designing an appropriate training procedure explicitly. minx f0(x) s.t. { fk(x)=0 ∀k = 1,...,nK { fl(x) ≤ 0 ∀l = nK + 1,...,nK +nL 11/15/2013
    35. 35. 11/15/2013
    36. 36. NEURAL NETWORK are computational models inspired by animal central nervous systems that are capable of machine learning and pattern recognition. They are usually presented as systems of interconnected neurons that can compute values from inputs by feeding information through the network. 11/15/2013
    37. 37. 11/15/2013
    38. 38. 11/15/2013
    39. 39. 11/15/2013
    40. 40. 11/15/2013
    41. 41. • Strong AI is hypothetical artificial intelligence that matches or exceeds human intelligence — the intelligence of a machine that could successfully perform any intellectual task that a human being can. • The skill to evolve itself is the most astonishing and at the same time dangerous skill which is used or shall be used in strong AI. • One proposal to deal with this is to ensure that the first generally intelligent AI is 'Friendly AI', and will then be able to control subsequently 11/15/2013 developed AIs.
    42. 42. 11/15/2013
    43. 43. Brain inc.

    ×