Introduction to Artificial Intelligence

Slides:



Advertisements
Similar presentations
Artificial Intelligence
Advertisements

Presentation on Artificial Intelligence
Aaron Summers. What is Artificial Intelligence (AI)? Great question right?
Artificial Intelligence for Games Game playing Patrick Olivier
Artificial Intelligence
An Introduction to Artificial Intelligence. Introduction Getting machines to “think”. Imitation game and the Turing test. Chinese room test. Key processes.
Introduction to Text Mining
Intelligence & Artificial Intelligence You must have a pre-prepared sentence or two to spout about what is a description of intelligence.. And what is.
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence From Data Mining To Knowledge.
Ch1 AI: History and Applications Dr. Bernard Chen Ph.D. University of Central Arkansas Spring 2011.
1 Lyle H. Ungar, University of Pennsylvania What is AI? “Artificial Intelligence is the study of how to make computers do things at which, at the moment,
CSC 9010 Spring Paula Matuszek A Brief Overview of Watson.
CSCI 4410 Introduction to Artificial Intelligence.
Artificial intelligence project
Artificial Intelligence
Machine Learning Lecture 1. Course Information Text book “Introduction to Machine Learning” by Ethem Alpaydin, MIT Press. Reference book “Data Mining.
Introduction to Artificial Intelligence Mitch Marcus CIS391 Fall, 2008.
I Robot.
Making Watson Fast Daniel Brown HON111. Need for Watson to be fast to play Jeopardy successfully – All computations have to be done in a few seconds –
WEEK INTRODUCTION IT440 ARTIFICIAL INTELLIGENCE.
Introduction to Text Mining Hongning Wang
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Introduction to Machine Learning © Roni Rosenfeld,
Adversarial Search and Game Playing Russell and Norvig: Chapter 5 Russell and Norvig: Chapter 6 CS121 – Winter 2003.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
Artificial Intelligence, simulation and modelling.
AI: AlphaGo European champion : Fan Hui A feat previously thought to be at least a decade away!!!
COMPUTER SYSTEM FUNDAMENTAL Genetic Computer School INTRODUCTION TO ARTIFICIAL INTELLIGENCE LESSON 11.
Artificial Intelligence
Introduction to Artificial Intelligence Heshaam Faili University of Tehran.
Overview of Artificial Intelligence (1) Artificial intelligence (AI) Computers with the ability to mimic or duplicate the functions of the human brain.
Teck Chia Partner, Exponent.vc
Introduction to Machine Learning
Artificial Intelligence, P.II
Artificial intelligence (AI)
More on Games Chapter 6 Some material adopted from notes by Charles R. Dyer, University of Wisconsin-Madison.
CHAPTER 1 Introduction BIC 3337 EXPERT SYSTEM.
Chapter 11: Artificial Intelligence
Artificial Intelligence: The Robots of Today
Siemens Enables Digitalization: Data Analytics & Artificial Intelligence Dr. Mike Roshchin, CT RDA BAM.
I Know it’s an Idiot But it’s MY artificial idiot!
COMP3710 Artificial Intelligence Thompson Rivers University
AlphaGo with Deep RL Alpha GO.
Videos NYT Video: DeepMind's alphaGo: Match 4 Summary: see 11 min.
CH. 1: Introduction 1.1 What is Machine Learning Example:
AlphaGO from Google DeepMind in 2016, beat human grandmasters
Impact Of Artificial Intelligence In Security Testing
Lots of news about Artificial Intelligence in the press
ARTIFICIAL INTELLIGENCE.
Basic Intro Tutorial on Machine Learning and Data Mining
Course Instructor: knza ch
Introduction Artificial Intelligent.
Artificial Intelligence introduction(2)
Introduction to Artificial Intelligence and Soft Computing
KNOWLEDGE REPRESENTATION
CS6700 Advanced AI Prof. Carla Gomes Prof. Bart Selman
TA : Mubarakah Otbi, Duaa al Ofi , Huda al Hakami
CSE 635 Multimedia Information Retrieval
Symbolic AI 2.0 Yi Zhou.
Future of Artificial Intelligence
Adversarial Search and Game Playing
COMP3710 Artificial Intelligence Thompson Rivers University
Artificial Intelligence and Future of Education
Artificial Intelligence
Artificial Intelligence in Medicine
These neural networks take a description of the Go board as an input and process it through 12 different network layers containing millions of neuron-like.
Machine Learning for Space Systems: Are We Ready?
Introduction to Artificial Intelligence
Artificial Intelligence Machine Learning
Presentation transcript:

Introduction to Artificial Intelligence 인공지능특론 부산대학교 권 혁 철

Artificial Intelligence until now “Narrow AI" was very different from the strong-AI fantasies that people painted. "AI programs are just a bunch of hacks," I thought. "This isn't intelligence; it's just people using computers to manipulate data and perform optimization, and they dress it up as 'AI' to make it sound sexy." Machine learning in particular seemed to be just a computer scientist's version of statistics. Neural networks were just an elaborated form of logistic regression.

Applications of AI previously Game playing Speech Recognition Natural Language Processing Computer Vision Expert systems Heuristic classification

Now on Health care Business integrity, business intelligence Knowledge discovery Enterprise knowledge management Security Customer support Support decision making Speech Understanding Natural Language Understanding Image Understanding

What do more AI in future Strong AI Sematic processing Automatic learning

Deep learning Gives the possibility of semantic processing by unsupervised learning ???? Word embedding in NLP Image recognition?

Chess Humans are still better at making up excuses. Name: Garry Kasparov Title: World Chess Champion Crime: Valued greed over common sense Humans are still better at making up excuses.

Perspective on Chess: Pro “Saying Deep Blue doesn’t really think about chess is like saying an airplane doesn't really fly because it doesn't flap its wings” Drew McDermott

Perspective on Chess: Con “Chess is the Drosophila of artificial intelligence. However, computer chess has developed much as genetics might have if the geneticists had concentrated their efforts starting in 1910 on breeding racing Drosophila. We would have some science, but mainly we would have very fast fruit flies.” John McCarthy 미국 스탠포드대 AI연구소 맥카시(John McCarthy)는 “바둑이야말로 인공지능의 초파리”라고 말했다. 초파리는 20세기 이후 멘델의 유전법칙을 증명하는 ‘복잡계’의 곤충이다. 인간의 줄기세포 연구에도 생쥐와 함께 등장한다. 미국의 컴퓨터 과학자인 힐스(Hills)는 “체스는 논리를 연구하는 초파리였다면 바둑은 직감을 연구하는 초파리”라고 했다. (참고문헌 이병두의 《인공지능 바둑》(북스홀릭, 2011))

바둑 구글이 개발한 인공지능 ‘알파고(AlphaGo)’ ??? 생성과 평가 모듈을 분리!! Google DeepMind Two neural networks paired with a new tree search algorithm has resulted in a Go program that was able to defeat the European champion 5-0 in October 다른 프로그램과 대결 Single computer: 499승 1패 Multiple computers: 1위 The distributed version was using 1,202 CPUs and 176 GPUs, about 25 times as many as the single-computer version 생성과 평가 모듈을 분리!!

The key to AlphaGo is reducing the enormous search space to something more manageable(David Silver and Demis Hassabis, from Google DeepMind) "One neural network, the 'policy network', predicts the next move, and is used to narrow the search to consider only the moves most likely to lead to a win. "The other neural network, the 'value network', is then used to reduce the depth of the search tree -- estimating the winner in each position in place of searching all the way to the end of the game.“ AlphaGo uses a Monte-Carlo tree search to look ahead to possible moves, with the neural networks suggesting moves and judging the board position. The system was trained on 30 million moves from games played by human experts, Google said, until it could predict the human move 57 percent of the time. Then it played against itself thousands of times. the most significant part of AlphaGo was not mastering Go, but rather using general-purpose learning techniques that could be applied to climate modelling or disease analysis.

빅 데이터 분석을 활용한 Watson Watson의 고급 분석 기술 능력은 3초 내에 답을 알아내기 위해서 2억 페이지의 데이터를 분석합니다.

Jeopardy Challenge Jeopardy Challenge requires advancing and incorporating a variety of QA technologies including parsing, question classification, question decomposition, automatic source acquisition and evaluation, entity and relation detection, logical form generation, and knowledge representation and reasoning

Watson Watson is a question answering (QA) computing system that IBM built to apply advanced natural language processing, information retrieval, knowledge representation, automated reasoning, and machine learning technologies to the field of open domain question answering developed in IBM's DeepQA project

Watson Watson is a question answering computer system capable of answering questions posed in natural language, Watson had access to 200 million pages of structured and unstructured content consuming four terabytes of disk storage including the full text of Wikipedia, but was not connected to the Internet during the game. encyclopedias, dictionaries, thesauri, newswire articles, and literary works. Watson also used databases, taxonomies, and ontologies. Specifically, DBPedia, WordNet, and Yago

IR-based Knowledge Acquisition Watson parses questions into different keywords and sentence fragments in order to find statistically related phrases. Watson's main innovation was not in the creation of a new algorithm for this operation but rather its ability to quickly execute hundreds of proven language analysis algorithms simultaneously to find the correct answer. Once Watson has a small number of potential solutions, it is able to check against its database to ascertain whether the solution makes sense.

Algorithm The questions and content are ambiguous and noisy and none of the individual algorithms are perfect. Therefore, each component must produce a confidence in its output, and individual component confidences must be combined to compute the overall confidence of the final answer. The final confidence is used to determine whether the computer system should risk choosing to answer at all.