1 Lecture 35 Brief Introduction to Main AI Areas (cont’d) Overview  Lecture Objective: Present the General Ideas on the AI Branches Below  Introduction.

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

Artificial Intelligence
Chapter 10 Artificial Intelligence © 2007 Pearson Addison-Wesley. All rights reserved.
1 Neural Networks - Basics Artificial Neural Networks - Basics Uwe Lämmel Business School Institute of Business Informatics
Brian Merrick CS498 Seminar.  Introduction to Neural Networks  Types of Neural Networks  Neural Networks with Pattern Recognition  Applications.
Artificial Intelligence (CS 461D)
LEARNING FROM OBSERVATIONS Yılmaz KILIÇASLAN. Definition Learning takes place as the agent observes its interactions with the world and its own decision-making.
1 Lecture 33 Introduction to Artificial Intelligence (AI) Overview  Lecture Objectives.  Introduction to AI.  The Turing Test for Intelligence.  Main.
Introduction to Neural Network Justin Jansen December 9 th 2002.
November 5, 2009Introduction to Cognitive Science Lecture 16: Symbolic vs. Connectionist AI 1 Symbolism vs. Connectionism There is another major division.
Artificial Intelligence
Rohit Ray ESE 251. What are Artificial Neural Networks? ANN are inspired by models of the biological nervous systems such as the brain Novel structure.
Artificial Intelligence (AI) Addition to the lecture 11.
Artificial Intelligence By Ryan Shoultes & Jeremy Creighton.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
Chapter 11: Artificial Intelligence
Artificial Intelligence Lecture No. 28 Dr. Asad Ali Safi ​ Assistant Professor, Department of Computer Science, COMSATS Institute of Information Technology.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
What is Artificial Intelligence? AI is the effort to develop systems that can behave/act like humans. Turing Test The problem = unrestricted domains –human.
计算机科学概述 Introduction to Computer Science 陆嘉恒 中国人民大学 信息学院
Neural Networks AI – Week 21 Sub-symbolic AI One: Neural Networks Lee McCluskey, room 3/10
Presentation on Neural Networks.. Basics Of Neural Networks Neural networks refers to a connectionist model that simulates the biophysical information.
Introduction GAM 376 Robin Burke Winter Outline Introductions Syllabus.
11 C H A P T E R Artificial Intelligence and Expert Systems.
Artificial Intelligence
1 Machine Learning The Perceptron. 2 Heuristic Search Knowledge Based Systems (KBS) Genetic Algorithms (GAs)
NEURAL NETWORKS FOR DATA MINING
Presented by Scott Lichtor An Introduction to Neural Networks.
Fundamentals of Information Systems, Third Edition2 Principles and Learning Objectives Artificial intelligence systems form a broad and diverse set of.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 11: Artificial Intelligence Computer Science: An Overview Tenth Edition.
Chapter 11 Artificial Intelligence Introduction to CS 1 st Semester, 2015 Sanghyun Park.
How Solvable Is Intelligence? A brief introduction to AI Dr. Richard Fox Department of Computer Science Northern Kentucky University.
1 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should.
I Robot.
Neural Networks in Computer Science n CS/PY 231 Lab Presentation # 1 n January 14, 2005 n Mount Union College.
Artificial Intelligence, Expert Systems, and Neural Networks Group 10 Cameron Kinard Leaundre Zeno Heath Carley Megan Wiedmaier.
Course Overview  What is AI?  What are the Major Challenges?  What are the Main Techniques?  Where are we failing, and why?  Step back and look at.
Dr.Abeer Mahmoud ARTIFICIAL INTELLIGENCE (CS 461D) Dr. Abeer Mahmoud Computer science Department Princess Nora University Faculty of Computer & Information.
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Intelligent Control Methods Lecture 2: Artificial Intelligence Slovak University of Technology Faculty of Material Science and Technology in Trnava.
Artificial Intelligence, simulation and modelling.
Artificial Intelligence Knowledge Representation.
Business Analytics Several odds and ends Copyright © 2016 Curt Hill.
Network Management Lecture 13. MACHINE LEARNING TECHNIQUES 2 Dr. Atiq Ahmed Université de Balouchistan.
March 31, 2016Introduction to Artificial Intelligence Lecture 16: Neural Network Paradigms I 1 … let us move on to… Artificial Neural Networks.
Artificial Neural Networks By: Steve Kidos. Outline Artificial Neural Networks: An Introduction Frank Rosenblatt’s Perceptron Multi-layer Perceptron Dot.
Overview of Artificial Intelligence (1) Artificial intelligence (AI) Computers with the ability to mimic or duplicate the functions of the human brain.
Brief Intro to Machine Learning CS539
Chapter 11: Artificial Intelligence
CHAPTER 1 Introduction BIC 3337 EXPERT SYSTEM.
Chapter 11: Artificial Intelligence
Artificial Intelligence (CS 370D)
Done Done Course Overview What is AI? What are the Major Challenges?
What is an ANN ? The inventor of the first neuro computer, Dr. Robert defines a neural network as,A human brain like system consisting of a large number.
CH. 1: Introduction 1.1 What is Machine Learning Example:
Basic Intro Tutorial on Machine Learning and Data Mining
Artificial Intelligence and Expert Systems
Artificial Intelligence
Artificial Intelligence Includes:
Chapter 12 Advanced Intelligent Systems
OVERVIEW OF BIOLOGICAL NEURONS
Overview of Machine Learning
3.1.1 Introduction to Machine Learning
The Naïve Bayes (NB) Classifier
ARTIFICIAL NEURAL networks.
Artificial Intelligence
Introduction to Neural Network
Sanguthevar Rajasekaran University of Connecticut
Presentation transcript:

1 Lecture 35 Brief Introduction to Main AI Areas (cont’d) Overview  Lecture Objective: Present the General Ideas on the AI Branches Below  Introduction to Main Areas of AI (cont’d):  Natural Language Processing  Introduction to Robotics  Neural Network  Machine Learning  Preview: Brief Introduction to Operating Systems

2 Lecture 35 I.Knowledge Representation l E.g., Facts:“bird isa animal” “bird has wings” » Logical Rules: “has-wings -> can-fly » (exception: isa penguin)” l Hierarchies and Relationships… animal bird pigeon living thing penguin colour blue (.5)colour grey (.5) wings feathers isa has

3 Lecture 35 Introduction to Natural Language Processing  Natural language refers to the languages that people speak (e.g., English).  Natural Language Processing deals with programming computers to understand natural human languages.  The goals of natural language processing is to train computers to be able to:  interpret human language  translate documents as humans would  Probably the single most challenging problem in computer science is to develop computers that can understand natural languages. So far, the complete solution to this problem has proved elusive, although a great deal of progress has been made.  Natural language was one of the first things that AI was envisioned to do, but it was found to be very difficult. It never succeeded as was hoped, as there is too much context and real world knowledge required.  Examples:  “John saw the elephant with a telescope.”  “The house was built by the river.”  “The house was built by the workers.”  “Time flies like an arrow.”  The context is assumed to resolve ambiguity. Other times it provides real information as well.

4 Lecture 35 Introduction to Robotics  Programming computers to see and hear and react to other sensory stimuli  Robots are now widely used in factories to perform high-precision jobs such as welding and riveting (fixing nails & tightening bolts)  They are also used in special situations that would be dangerous for humans -- for example, in cleaning toxic wastes or defusing bombs.  Although great advances have been made in the field of robotics during the last decade, robots are still not very useful in everyday life, as they are too clumsy to perform ordinary household chores.

5 Lecture 35 Introduction to Neural Networks  The human brain is so powerful because of its ability to process information in parallel. The brain consists of billions of neurons, each connected to thousands of others. Each neuron acts as its own processing unit, and works together with other neurons, exchanging information to create our perception, motor and creative abilities.  The human brain is said to contain about neurons and about interconnections (roughly equivalent to the number of characters in 10 billion books each of 350 pages)!

6 Lecture 35 Introduction to Neural Networks (cont’d)  Neural Networks: are AI systems that simulate intelligence by attempting to reproduce the types of physical connections that occur in animal brains. A neural network uses adaptive algorithms, that “learn” based on training data.

7 Lecture 35 Introduction to Neural Networks (cont’d)  An ANN can be viewed as a graph in which the nodes represent neurons and the arcs represent axons (i.e., the interneuronal connections).  The nodes in an ANN get weighted input from other nodes according to the pattern of connectivity expressed in the graph.  The weight represent the importance of the interconnections and in the ANN are initially assigned random values.  When the sum of all inputs on a given node exceeds a certain threshold, the node fires and an output value is propagated through the preset interconnections of the graph.  Neural networks provides good solutions for recognition and classification problems

8 Lecture 35 Introduction to Machine Learning  What is learning?  "Learning denotes changes in a system that enable a system to do the same task more efficiently the next time.”  The ability of the system to improve its behavior  It could be reorganization of existing knowledge  Why it is hard?  Intelligence implies that an organism or machine must be able to adapt to new situations.  It must be able to learn to do new things.  This requires knowledge acquisition, inference, updating/refinement of knowledge base, acquisition of heuristics, applying faster searches, etc.

9 Lecture 35 Learning Paradigms  Rote Learning : memorizing  Inductive vs. deductive learning:  inductive: from special cases to general rules  deductive: from general rules to special cases  Supervised Learning:  give the training set with the right answer, the teacher evaluates the student answer and give the right answer.  Reinforcement Learning:  the teacher evaluates the students paper and give a grade to his paper without telling the correct answer to the student.  Unsupervised Learning:  You browse the web pages and you categorize them according to certain trend you develop while reading these web pages. No teacher.  Discovery : Unsupervised, specific goal not given  Reinforcement : Only feedback (positive or negative reward) given at end of a sequence of steps. Requires assigning reward to steps by solving the credit assignment problem--which steps should receive credit or blame for a final result?