SlideShare a Scribd company logo
1 of 32
A
POWERPOINT PRESENTATION
            ON
 ARTIFICIAL INTELLIGENCE
CONTENTS
• ARTIFICIAL INTELLIGENCE
• ARTIFICIAL NEURAL NETWORK IN MEDICAL
  FIELD
• LEARNING ALGORITHMS
• CHARACTERISTICS OF AI & ANN
ARTIFICIAL INTELLIGENCE
  The Term A.I. belongs to a Fifth Generation Computer System
In which the System works in the same manner as human-being.



                                             In another sense,
                                               we can term it
                                        As the study and design of
                                            Intelligent Agents.
The field of AI research was founded at a conference on
the campus of Dartmouth College in the summer of 1956.
    The attendees, including John McCarthy, Marvin
 Minsky, Allen Newell and Herbert Simon, became the
 leaders of AI research for many decades. They and their
    students wrote programs that were, to most people,
     simply astonishing: computers were solving word
    problems in algebra, proving logical theorems and
                     speaking English.
By the middle of the 1960s, research in the U.S. was
    heavily funded by the Department of Defense and
 laboratories had been established around the world. AI's
founders were profoundly optimistic about the future of the
new field: Herbert Simon predicted that "machines will be
capable, within twenty years, of doing any work a man can
  do" and Marvin Minsky agreed, writing that "within a
generation ... the problem of creating 'artificial intelligence'
                 will substantially be solved".
In 1974, in response to the criticism of England's Sir
James Lighthill and ongoing pressure from Congress to
   fund more productive projects, the U.S. and British
governments cut off all undirected, exploratory research
  in AI. The next few years, when funding for projects
 was hard to find, would later be called an "AI winter".
The most difficult problems in knowledge representation are:

                         •Default Reasoning
                        •Qualification Problem

Knowledge representation and knowledge engineering are central to
AI research. Many of the problems machines are expected to solve
will require extensive knowledge about the world. Among the things
that AI needs to represent are: objects, properties, categories and
relations between objects; situations, events, states and time; causes
and effects; knowledge about knowledge (what we know about what
other people know); and many other, less well researched domains.
A complete representation of "what exists" is an ontology (borrowing
a word from traditional philosophy), of which the most general are
called upper ontologies.
Natural language processing gives machines the ability to
 read and understand the languages that humans speak.


                        Many researchers hope that a sufficiently
                           powerful natural language processing
                       system would be able to acquire knowledge
                          on its own, by reading the existing text
                             available over the internet. Some
                          straightforward applications of natural
                         language processing include information
                           retrieval (or text mining) and machine
                                          translation.
Emotion and social skills play two roles for an intelligent
  agent.
• First, it must be able to predict the actions of others, by
  understanding their motives and emotional states. (This
  involves elements of game theory, decision theory, as well
  as the ability to model human emotions and the
  perceptual skills to detect emotions.)
• Also, for good human-computer interaction, an intelligent
  machine also needs to display emotions. At the very least
  it must appear polite and sensitive to the humans it
  interacts with. At best, it should have normal emotions
  itself
• Example is Kismet, a robot with rudimentary social skills
TOPIO, a robot that can
                                   play table tennis,
 A sub-field of AI addresses      developed by TOSY.
creativity both theoretically
    (from a philosophical
      And psychological
         perspective)
        And practically
         (via specific
       implementations
        of systems that
       generate outputs
          that can be
     considered creative)
Artificial neurons
         Neurons work by processing information. They receive and provide information
         in form of spikes.

           x1
                                      w1
           x2
           x3                   w2                                         Output
                                                 n
           …                               z          wi xi ; y   H ( z)
Inputs




                      w3                        i 1                               y
           xn-1   .
                      . w
           xn           . n-1

                                     wn

                                               The McCullogh-Pitts model
Artificial neurons

The McCullogh-Pitts model:
   • spikes are interpreted as spike rates;
   • synaptic strength are translated as synaptic weights;
   • excitation means positive product between the
   incoming spike rate and the corresponding synaptic
   weight;
   • inhibition means negative product between the
   incoming spike rate and the corresponding synaptic
   weight;
Summary
• Artificial
           neural networks are inspired by the learning
processes that take place in biological systems.
• Artificial neurons and neural networks try to imitate the
working mechanisms of their biological counterparts.
• Learning can be perceived as an optimisation process.
• Biological neural learning happens by the modification
of the synaptic strength. Artificial neural networks learn
in the same way.
• The synapse strength modification rules for artificial
neural networks can be derived by applying mathematical
optimisation methods.
Summary
• Learning tasks of artificial neural networks can be
reformulated as function approximation tasks.
• Neural networks can be considered as nonlinear function
approximating tools (i.e., linear combinations of nonlinear
basis functions), where the parameters of the networks
should be found by applying optimisation methods.
• The optimisation is done with respect to the approximation
error measure.
• In general it is enough to have a single hidden layer neural
network to learn the approximation of a nonlinear function.
In such cases general optimisation can be applied to find the
change rules for the synaptic weights.
Learning is acquiring new, or modifying
existing, knowledge, behaviors, skills, values, or preferences and may involve
                 synthesizing different types of information.

 The ability to learn is possessed by humans, animals and some machines.
            Progress over time tends to follow learning curves.

  Human learning may occur as part of education, personal development,
                        schooling, or training.

  There is evidence for human behavioral learning prenatally, in which
habituation has been observed as early as 32 weeks into gestation, indicating
  that the central nervous system is sufficiently developed and primed for
        learning and memory to occur very early on in development.
Supervised Learning

• It is based on a
  labeled training set.                                 Class



• The class of each
                                   Class
                                                A
  piece of data in                     B                    Class


  training set is known.
                           Class
                                                    B
• Class labels are pre-
                                   A
  determined and                                    A       Class



  provided in the                   Class   B
  training phase.
Unsupervised Learning
• Input : set of patterns P, from n-dimensional space S, but
  little/no information about their classification, evaluation,
  interesting features, etc.
  It must learn these by itself! : )

• Tasks:
   – Clustering - Group patterns based on similarity
   – Vector Quantization - Fully divide up S into a small set of
     regions (defined by codebook vectors) that also helps
     cluster P.
   – Feature Extraction - Reduce dimensionality of S by
     removing unimportant features (i.e. those that do not help
     in clustering P)
Reinforcement Learning
• Mainly based on
  “Reinforcement
  Learning – An
  Introduction” by
  Richard Sutton and
  Andrew Barto
Learning from Experience Plays a Role in
                  …
                    Artificial Intelligence



                                                        Control Theory and
                                                        Operations Research
Psychology

                                    Reinforcement
                                     Learning (RL)




     Neuroscience
                                          Artificial Neural Networks
Multilayer Perceptrons
             Architecture


Input                            Output
layer                             layer




            Hidden Layers
Backpropagation Algorithm

• Two phases of computation:

  – Forward pass: run the NN and compute the error for each
    neuron of the output layer.



  – Backward pass: start at the output layer, and pass the errors
    backwards through the network, layer by layer, by
    recursively computing the local gradient of each neuron.


                                                                21
Delta Rule

• Functions more like nonlinear parameter fitting - the goal is to
  exactly reproduce the output, Y, by incremental methods.



• Thus, weights will not grow without bound unless learning
  rate is too high.



• Learning rate is determined by modeler - it constrains the size
  of the weight changes.
CHARACTERISTICS OF AI &ANN

 In the field of robotic minimally invasive surgery, it is apparent that advances
in technology have conferred increased precision during—and the decreased risk
of complications after—a wide range of surgical procedures.

 Patients who are operated on by robots controlled by surgeons enjoy shorter
recovery times and fewer visible post-operative scars than those subject to
traditional open-surgical procedures.

 With advances in robotic technology in the operating room, though, the
surgeon's hand is no longer the driving force behind the scalpel.
THE POTENTIAL AND THE PROCESS

• In recent years, a great deal of effort has been devoted to
  development of methodologies for cancer therapy.

• Among them; Heavy Iron therapy is highly under attention.

• We fixed an ultrasonic diagnosis device on the top of a robot
  arm and tracked the cancer which was moved on a monitor
  with respiration.

• By using the neural network, it became possible to track the
  cancer automatically.
THE BASIC WORKING CONDITION FOR
         CANCER DIAGNOSIS

• Neural networks provide a unique computing archi-tecture
  whose potential has only began to be tapped, Used to address
  problems that are intractable or cum-bersome with traditional
  methods, these new comput-ing architectures, inspired by the
  structure of the brain.



• Artificial neural networks take their name from the networks
  of nerve cells in the brain.
• In a neural network each neuron is linked to many of its
  neighbors (typically hundreds or thousands) so that there are
  many more interconnects than neurons.

• The power of the neural network lies in the tremendous number
  of interconnections.

• The neuron performs a weighted sum on the inputs and uses a
  nonlinear threshold function to compute its output.

• The calculated result is sent along the output connections to the
  target cell.
RESPIRATION
• The respiration information which is fed into the de-signed
  neural network as input is a waveform obtained by a strain
  gage in of line.

• We fixed the strain gauge around the abdomen and sensor
  expanded and contracting by abdominal movement, the
  changes is taken as respiration information.

• Then, the informa-tion of respiration (both amplitude and
  differential at period ) are fed into the neural network.
ROBOT ARM
• The robot arm used in this study is a multi-joint manipulator
  with 6 degree-of-freedom.

• Flappers which show the coordinates of diagnosis device
  position are x, y, z and the rotation.

• In simulation, since we controlled it in Y axis direction, the
  variable parameter is y' only and another parameters (in this
  case X,Z axis) are consistant.
Robot Arm
SIMULATION
• The displacement prediction network and inverse kinematics
  networks were obtained by using a neural network simulator
  developed by University of Toronto called "Xenon".

• We combined two networks (combination network), and it
  gave its output to the robot arm input.

•    Using the trained network and off line respiration data, we
    controlled the robot arm in one din-tension automatically.
Artificial intelligence
Artificial intelligence

More Related Content

What's hot

Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overview
butest
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
vallibhargavi
 
Artificial Intelligence Course- Introduction
Artificial Intelligence Course- IntroductionArtificial Intelligence Course- Introduction
Artificial Intelligence Course- Introduction
Muhammad Sanaullah
 

What's hot (20)

Artificial Intelligence and Mathematics
Artificial Intelligence and MathematicsArtificial Intelligence and Mathematics
Artificial Intelligence and Mathematics
 
Artificial Intelligence Techniques In Power Systems Paper Presentation
Artificial Intelligence Techniques In Power Systems Paper PresentationArtificial Intelligence Techniques In Power Systems Paper Presentation
Artificial Intelligence Techniques In Power Systems Paper Presentation
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
 
Introduction to Artificial Intelligence
Introduction to Artificial IntelligenceIntroduction to Artificial Intelligence
Introduction to Artificial Intelligence
 
Lecture 02 introduction to ai
Lecture 02 introduction to aiLecture 02 introduction to ai
Lecture 02 introduction to ai
 
DWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
DWX 2018 Session about Artificial Intelligence, Machine and Deep LearningDWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
DWX 2018 Session about Artificial Intelligence, Machine and Deep Learning
 
Artificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and OverviewArtificial Intelligence AI Topics History and Overview
Artificial Intelligence AI Topics History and Overview
 
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Ai notes
Ai notesAi notes
Ai notes
 
Ai ml dl_bct and mariners-1
Ai  ml dl_bct and mariners-1Ai  ml dl_bct and mariners-1
Ai ml dl_bct and mariners-1
 
Useful Techniques in Artificial Intelligence
Useful Techniques in Artificial IntelligenceUseful Techniques in Artificial Intelligence
Useful Techniques in Artificial Intelligence
 
Towards which Intelligence? Cognition as Design Key for building Artificial I...
Towards which Intelligence? Cognition as Design Key for building Artificial I...Towards which Intelligence? Cognition as Design Key for building Artificial I...
Towards which Intelligence? Cognition as Design Key for building Artificial I...
 
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
 
Artificial Intelligence Course- Introduction
Artificial Intelligence Course- IntroductionArtificial Intelligence Course- Introduction
Artificial Intelligence Course- Introduction
 
Paper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applicationsPaper sharing_deep learning for smart manufacturing methods and applications
Paper sharing_deep learning for smart manufacturing methods and applications
 
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
Past, Present and Future of AI: a Fascinating Journey - Ramon Lopez de Mantar...
 
Artificial Intelligence, Machine Learning and Deep Learning with CNN
Artificial Intelligence, Machine Learning and Deep Learning with CNNArtificial Intelligence, Machine Learning and Deep Learning with CNN
Artificial Intelligence, Machine Learning and Deep Learning with CNN
 
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
 
Introduction to artificial intelligence
Introduction to artificial intelligenceIntroduction to artificial intelligence
Introduction to artificial intelligence
 

Viewers also liked

artificial intelligence
artificial intelligenceartificial intelligence
artificial intelligence
vallibhargavi
 
Web Messenger
Web MessengerWeb Messenger
Web Messenger
samonji13
 
The era of artificial intelligence
The era of artificial intelligenceThe era of artificial intelligence
The era of artificial intelligence
Prajjwal Kushwaha
 

Viewers also liked (20)

Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
What is artificial intelligence
What is artificial intelligenceWhat is artificial intelligence
What is artificial intelligence
 
Heuristic Search Techniques {Artificial Intelligence}
Heuristic Search Techniques {Artificial Intelligence}Heuristic Search Techniques {Artificial Intelligence}
Heuristic Search Techniques {Artificial Intelligence}
 
Hill climbing
Hill climbingHill climbing
Hill climbing
 
AI: Learning in AI
AI: Learning in AI AI: Learning in AI
AI: Learning in AI
 
artificial intelligence
artificial intelligenceartificial intelligence
artificial intelligence
 
Web Messenger
Web MessengerWeb Messenger
Web Messenger
 
Roy
RoyRoy
Roy
 
Magz adverts&covers
Magz adverts&coversMagz adverts&covers
Magz adverts&covers
 
The era of artificial intelligence
The era of artificial intelligenceThe era of artificial intelligence
The era of artificial intelligence
 
2015 Artificial Intelligence Techniques at Engineering Seminar - Chapter 2 - ...
2015 Artificial Intelligence Techniques at Engineering Seminar - Chapter 2 - ...2015 Artificial Intelligence Techniques at Engineering Seminar - Chapter 2 - ...
2015 Artificial Intelligence Techniques at Engineering Seminar - Chapter 2 - ...
 
08 neural networks(1).unlocked
08 neural networks(1).unlocked08 neural networks(1).unlocked
08 neural networks(1).unlocked
 
AI in life extension
AI in life extensionAI in life extension
AI in life extension
 
Baye's rule
Baye's ruleBaye's rule
Baye's rule
 
DFS BFS and UCS in R
DFS BFS and UCS in RDFS BFS and UCS in R
DFS BFS and UCS in R
 
Predicate Calculus
Predicate CalculusPredicate Calculus
Predicate Calculus
 
Government Policies for Entrepreneurs
Government Policies for EntrepreneursGovernment Policies for Entrepreneurs
Government Policies for Entrepreneurs
 
Mobile Instant Messaging
Mobile Instant MessagingMobile Instant Messaging
Mobile Instant Messaging
 
Ai and neural networks
Ai and neural networksAi and neural networks
Ai and neural networks
 
Power Point Presentation on Artificial Intelligence
Power Point Presentation on Artificial Intelligence Power Point Presentation on Artificial Intelligence
Power Point Presentation on Artificial Intelligence
 

Similar to Artificial intelligence

Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
Francesco Collova'
 
Lect1_Threshold_Logic_Unit lecture 1 - ANN
Lect1_Threshold_Logic_Unit  lecture 1 - ANNLect1_Threshold_Logic_Unit  lecture 1 - ANN
Lect1_Threshold_Logic_Unit lecture 1 - ANN
MostafaHazemMostafaa
 
Learning
LearningLearning
Learning
butest
 
artificial intelligence
 artificial intelligence artificial intelligence
artificial intelligence
Megha Sharma
 

Similar to Artificial intelligence (20)

Abhinav
AbhinavAbhinav
Abhinav
 
1 Introduction to AI.pptx
1 Introduction to AI.pptx1 Introduction to AI.pptx
1 Introduction to AI.pptx
 
Ai introduction
Ai introductionAi introduction
Ai introduction
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
 
nncollovcapaldo2013-131220052427-phpapp01.pdf
nncollovcapaldo2013-131220052427-phpapp01.pdfnncollovcapaldo2013-131220052427-phpapp01.pdf
nncollovcapaldo2013-131220052427-phpapp01.pdf
 
nncollovcapaldo2013-131220052427-phpapp01.pdf
nncollovcapaldo2013-131220052427-phpapp01.pdfnncollovcapaldo2013-131220052427-phpapp01.pdf
nncollovcapaldo2013-131220052427-phpapp01.pdf
 
Lecture 1.ppt
Lecture 1.pptLecture 1.ppt
Lecture 1.ppt
 
Artificial intelligent Lec 1-ai-introduction-
Artificial intelligent Lec 1-ai-introduction-Artificial intelligent Lec 1-ai-introduction-
Artificial intelligent Lec 1-ai-introduction-
 
Lec1 introduction
Lec1 introductionLec1 introduction
Lec1 introduction
 
Lect1_Threshold_Logic_Unit lecture 1 - ANN
Lect1_Threshold_Logic_Unit  lecture 1 - ANNLect1_Threshold_Logic_Unit  lecture 1 - ANN
Lect1_Threshold_Logic_Unit lecture 1 - ANN
 
Ai history to-m-learning
Ai history to-m-learningAi history to-m-learning
Ai history to-m-learning
 
Lecture 01
Lecture 01Lecture 01
Lecture 01
 
Artificial intellegence by Bhanuprakash
Artificial  intellegence by BhanuprakashArtificial  intellegence by Bhanuprakash
Artificial intellegence by Bhanuprakash
 
AI Introduction
AI Introduction AI Introduction
AI Introduction
 
Learning
LearningLearning
Learning
 
01_Artificial_Intelligence-Introduction.ppt
01_Artificial_Intelligence-Introduction.ppt01_Artificial_Intelligence-Introduction.ppt
01_Artificial_Intelligence-Introduction.ppt
 
artificial intelligence
 artificial intelligence artificial intelligence
artificial intelligence
 
01 introduction
01 introduction01 introduction
01 introduction
 
Artificial_Intelligence.ppt
Artificial_Intelligence.pptArtificial_Intelligence.ppt
Artificial_Intelligence.ppt
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 

More from HITESH Kumawat

Intermediate band quantum dot solar cell
Intermediate band quantum dot solar cellIntermediate band quantum dot solar cell
Intermediate band quantum dot solar cell
HITESH Kumawat
 
Future technology trends and gadgets
Future technology trends and gadgetsFuture technology trends and gadgets
Future technology trends and gadgets
HITESH Kumawat
 
Touch screen technology
Touch screen technologyTouch screen technology
Touch screen technology
HITESH Kumawat
 
Autonomous Fire detection Robot
Autonomous Fire detection Robot Autonomous Fire detection Robot
Autonomous Fire detection Robot
HITESH Kumawat
 
INFRARED TEMPERATURE DETECTOR
INFRARED TEMPERATURE DETECTORINFRARED TEMPERATURE DETECTOR
INFRARED TEMPERATURE DETECTOR
HITESH Kumawat
 
T rays technology in future scanners
T rays technology in future scannersT rays technology in future scanners
T rays technology in future scanners
HITESH Kumawat
 
Tracking and positioning_of_mobile_systems_in_telecom_network_2
Tracking and positioning_of_mobile_systems_in_telecom_network_2Tracking and positioning_of_mobile_systems_in_telecom_network_2
Tracking and positioning_of_mobile_systems_in_telecom_network_2
HITESH Kumawat
 

More from HITESH Kumawat (12)

Intermediate band quantum dot solar cell
Intermediate band quantum dot solar cellIntermediate band quantum dot solar cell
Intermediate band quantum dot solar cell
 
Future technology trends and gadgets
Future technology trends and gadgetsFuture technology trends and gadgets
Future technology trends and gadgets
 
Touch screen technology
Touch screen technologyTouch screen technology
Touch screen technology
 
Blue eyes
Blue eyesBlue eyes
Blue eyes
 
RED TACTON
RED TACTONRED TACTON
RED TACTON
 
Autonomous Fire detection Robot
Autonomous Fire detection Robot Autonomous Fire detection Robot
Autonomous Fire detection Robot
 
INFRARED TEMPERATURE DETECTOR
INFRARED TEMPERATURE DETECTORINFRARED TEMPERATURE DETECTOR
INFRARED TEMPERATURE DETECTOR
 
T rays technology in future scanners
T rays technology in future scannersT rays technology in future scanners
T rays technology in future scanners
 
Tracking and positioning_of_mobile_systems_in_telecom_network_2
Tracking and positioning_of_mobile_systems_in_telecom_network_2Tracking and positioning_of_mobile_systems_in_telecom_network_2
Tracking and positioning_of_mobile_systems_in_telecom_network_2
 
Ktps presentation
Ktps presentationKtps presentation
Ktps presentation
 
RAPS
RAPSRAPS
RAPS
 
Optical computing1
Optical computing1Optical computing1
Optical computing1
 

Artificial intelligence

  • 1. A POWERPOINT PRESENTATION ON ARTIFICIAL INTELLIGENCE
  • 2. CONTENTS • ARTIFICIAL INTELLIGENCE • ARTIFICIAL NEURAL NETWORK IN MEDICAL FIELD • LEARNING ALGORITHMS • CHARACTERISTICS OF AI & ANN
  • 3. ARTIFICIAL INTELLIGENCE The Term A.I. belongs to a Fifth Generation Computer System In which the System works in the same manner as human-being. In another sense, we can term it As the study and design of Intelligent Agents.
  • 4. The field of AI research was founded at a conference on the campus of Dartmouth College in the summer of 1956. The attendees, including John McCarthy, Marvin Minsky, Allen Newell and Herbert Simon, became the leaders of AI research for many decades. They and their students wrote programs that were, to most people, simply astonishing: computers were solving word problems in algebra, proving logical theorems and speaking English.
  • 5. By the middle of the 1960s, research in the U.S. was heavily funded by the Department of Defense and laboratories had been established around the world. AI's founders were profoundly optimistic about the future of the new field: Herbert Simon predicted that "machines will be capable, within twenty years, of doing any work a man can do" and Marvin Minsky agreed, writing that "within a generation ... the problem of creating 'artificial intelligence' will substantially be solved".
  • 6. In 1974, in response to the criticism of England's Sir James Lighthill and ongoing pressure from Congress to fund more productive projects, the U.S. and British governments cut off all undirected, exploratory research in AI. The next few years, when funding for projects was hard to find, would later be called an "AI winter".
  • 7. The most difficult problems in knowledge representation are: •Default Reasoning •Qualification Problem Knowledge representation and knowledge engineering are central to AI research. Many of the problems machines are expected to solve will require extensive knowledge about the world. Among the things that AI needs to represent are: objects, properties, categories and relations between objects; situations, events, states and time; causes and effects; knowledge about knowledge (what we know about what other people know); and many other, less well researched domains. A complete representation of "what exists" is an ontology (borrowing a word from traditional philosophy), of which the most general are called upper ontologies.
  • 8. Natural language processing gives machines the ability to read and understand the languages that humans speak. Many researchers hope that a sufficiently powerful natural language processing system would be able to acquire knowledge on its own, by reading the existing text available over the internet. Some straightforward applications of natural language processing include information retrieval (or text mining) and machine translation.
  • 9. Emotion and social skills play two roles for an intelligent agent. • First, it must be able to predict the actions of others, by understanding their motives and emotional states. (This involves elements of game theory, decision theory, as well as the ability to model human emotions and the perceptual skills to detect emotions.) • Also, for good human-computer interaction, an intelligent machine also needs to display emotions. At the very least it must appear polite and sensitive to the humans it interacts with. At best, it should have normal emotions itself • Example is Kismet, a robot with rudimentary social skills
  • 10. TOPIO, a robot that can play table tennis, A sub-field of AI addresses developed by TOSY. creativity both theoretically (from a philosophical And psychological perspective) And practically (via specific implementations of systems that generate outputs that can be considered creative)
  • 11. Artificial neurons Neurons work by processing information. They receive and provide information in form of spikes. x1 w1 x2 x3 w2 Output n … z wi xi ; y H ( z) Inputs w3 i 1 y xn-1 . . w xn . n-1 wn The McCullogh-Pitts model
  • 12. Artificial neurons The McCullogh-Pitts model: • spikes are interpreted as spike rates; • synaptic strength are translated as synaptic weights; • excitation means positive product between the incoming spike rate and the corresponding synaptic weight; • inhibition means negative product between the incoming spike rate and the corresponding synaptic weight;
  • 13. Summary • Artificial neural networks are inspired by the learning processes that take place in biological systems. • Artificial neurons and neural networks try to imitate the working mechanisms of their biological counterparts. • Learning can be perceived as an optimisation process. • Biological neural learning happens by the modification of the synaptic strength. Artificial neural networks learn in the same way. • The synapse strength modification rules for artificial neural networks can be derived by applying mathematical optimisation methods.
  • 14. Summary • Learning tasks of artificial neural networks can be reformulated as function approximation tasks. • Neural networks can be considered as nonlinear function approximating tools (i.e., linear combinations of nonlinear basis functions), where the parameters of the networks should be found by applying optimisation methods. • The optimisation is done with respect to the approximation error measure. • In general it is enough to have a single hidden layer neural network to learn the approximation of a nonlinear function. In such cases general optimisation can be applied to find the change rules for the synaptic weights.
  • 15. Learning is acquiring new, or modifying existing, knowledge, behaviors, skills, values, or preferences and may involve synthesizing different types of information.  The ability to learn is possessed by humans, animals and some machines. Progress over time tends to follow learning curves. Human learning may occur as part of education, personal development, schooling, or training. There is evidence for human behavioral learning prenatally, in which habituation has been observed as early as 32 weeks into gestation, indicating that the central nervous system is sufficiently developed and primed for learning and memory to occur very early on in development.
  • 16. Supervised Learning • It is based on a labeled training set. Class • The class of each Class A piece of data in B Class training set is known. Class B • Class labels are pre- A determined and A Class provided in the Class B training phase.
  • 17. Unsupervised Learning • Input : set of patterns P, from n-dimensional space S, but little/no information about their classification, evaluation, interesting features, etc. It must learn these by itself! : ) • Tasks: – Clustering - Group patterns based on similarity – Vector Quantization - Fully divide up S into a small set of regions (defined by codebook vectors) that also helps cluster P. – Feature Extraction - Reduce dimensionality of S by removing unimportant features (i.e. those that do not help in clustering P)
  • 18. Reinforcement Learning • Mainly based on “Reinforcement Learning – An Introduction” by Richard Sutton and Andrew Barto
  • 19. Learning from Experience Plays a Role in … Artificial Intelligence Control Theory and Operations Research Psychology Reinforcement Learning (RL) Neuroscience Artificial Neural Networks
  • 20. Multilayer Perceptrons Architecture Input Output layer layer Hidden Layers
  • 21. Backpropagation Algorithm • Two phases of computation: – Forward pass: run the NN and compute the error for each neuron of the output layer. – Backward pass: start at the output layer, and pass the errors backwards through the network, layer by layer, by recursively computing the local gradient of each neuron. 21
  • 22. Delta Rule • Functions more like nonlinear parameter fitting - the goal is to exactly reproduce the output, Y, by incremental methods. • Thus, weights will not grow without bound unless learning rate is too high. • Learning rate is determined by modeler - it constrains the size of the weight changes.
  • 23. CHARACTERISTICS OF AI &ANN  In the field of robotic minimally invasive surgery, it is apparent that advances in technology have conferred increased precision during—and the decreased risk of complications after—a wide range of surgical procedures.  Patients who are operated on by robots controlled by surgeons enjoy shorter recovery times and fewer visible post-operative scars than those subject to traditional open-surgical procedures.  With advances in robotic technology in the operating room, though, the surgeon's hand is no longer the driving force behind the scalpel.
  • 24. THE POTENTIAL AND THE PROCESS • In recent years, a great deal of effort has been devoted to development of methodologies for cancer therapy. • Among them; Heavy Iron therapy is highly under attention. • We fixed an ultrasonic diagnosis device on the top of a robot arm and tracked the cancer which was moved on a monitor with respiration. • By using the neural network, it became possible to track the cancer automatically.
  • 25. THE BASIC WORKING CONDITION FOR CANCER DIAGNOSIS • Neural networks provide a unique computing archi-tecture whose potential has only began to be tapped, Used to address problems that are intractable or cum-bersome with traditional methods, these new comput-ing architectures, inspired by the structure of the brain. • Artificial neural networks take their name from the networks of nerve cells in the brain.
  • 26. • In a neural network each neuron is linked to many of its neighbors (typically hundreds or thousands) so that there are many more interconnects than neurons. • The power of the neural network lies in the tremendous number of interconnections. • The neuron performs a weighted sum on the inputs and uses a nonlinear threshold function to compute its output. • The calculated result is sent along the output connections to the target cell.
  • 27. RESPIRATION • The respiration information which is fed into the de-signed neural network as input is a waveform obtained by a strain gage in of line. • We fixed the strain gauge around the abdomen and sensor expanded and contracting by abdominal movement, the changes is taken as respiration information. • Then, the informa-tion of respiration (both amplitude and differential at period ) are fed into the neural network.
  • 28. ROBOT ARM • The robot arm used in this study is a multi-joint manipulator with 6 degree-of-freedom. • Flappers which show the coordinates of diagnosis device position are x, y, z and the rotation. • In simulation, since we controlled it in Y axis direction, the variable parameter is y' only and another parameters (in this case X,Z axis) are consistant.
  • 30. SIMULATION • The displacement prediction network and inverse kinematics networks were obtained by using a neural network simulator developed by University of Toronto called "Xenon". • We combined two networks (combination network), and it gave its output to the robot arm input. • Using the trained network and off line respiration data, we controlled the robot arm in one din-tension automatically.