Pedro Domingos University of Washington. Traditional Programming Machine Learning Computer Data Algorithm Output Computer Data Output Algorithm.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California
Advertisements

Markov Logic Networks Instructor: Pedro Domingos.
Review Markov Logic Networks Mathew Richardson Pedro Domingos Xinran(Sean) Luo, u
Biologically Inspired AI (mostly GAs). Some Examples of Biologically Inspired Computation Neural networks Evolutionary computation (e.g., genetic algorithms)
Institute of Intelligent Power Electronics – IPE Page1 Introduction to Basics of Genetic Algorithms Docent Xiao-Zhi Gao Department of Electrical Engineering.
Markov Logic: A Unifying Framework for Statistical Relational Learning Pedro Domingos Matthew Richardson
Hidden Markov Models First Story! Majid Hajiloo, Aria Khademi.
1 Lecture 35 Brief Introduction to Main AI Areas (cont’d) Overview  Lecture Objective: Present the General Ideas on the AI Branches Below  Introduction.
Brian Merrick CS498 Seminar.  Introduction to Neural Networks  Types of Neural Networks  Neural Networks with Pattern Recognition  Applications.
10/28 Temporal Probabilistic Models. Temporal (Sequential) Process A temporal process is the evolution of system state over time Often the system state.
CSE 574 – Artificial Intelligence II Statistical Relational Learning Instructor: Pedro Domingos.
Recursive Random Fields Daniel Lowd University of Washington June 29th, 2006 (Joint work with Pedro Domingos)
EECS 349 Machine Learning Instructor: Doug Downey Note: slides adapted from Pedro Domingos, University of Washington, CSE
Big Ideas in Cmput366. Search Blind Search Iterative deepening Heuristic Search A* Local and Stochastic Search Randomized algorithm Constraint satisfaction.
CSE 546 Data Mining Machine Learning Instructor: Pedro Domingos.
CSE 574: Artificial Intelligence II Statistical Relational Learning Instructor: Pedro Domingos.
Recursive Random Fields Daniel Lowd University of Washington (Joint work with Pedro Domingos)
CSE 590ST Statistical Methods in Computer Science Instructor: Pedro Domingos.
Intelligent Legged Robot Systems AME498Q/598I Intelligent Systems 19NOV03.
Statistical Relational Learning Pedro Domingos Dept. Computer Science & Eng. University of Washington.
Genetic Programming. Agenda What is Genetic Programming? Background/History. Why Genetic Programming? How Genetic Principles are Applied. Examples of.
CSE 515 Statistical Methods in Computer Science Instructor: Pedro Domingos.
Function Approximation for Imitation Learning in Humanoid Robots Rajesh P. N. Rao Dept of Computer Science and Engineering University of Washington,
AI Overview Reference: "Artificial Intelligence, a Modern Approach, 3 rd ed."
A simple method for multi-relational outlier detection Sarah Riahi and Oliver Schulte School of Computing Science Simon Fraser University Vancouver, Canada.
How We’re Going to Solve the AI Problem Pedro Domingos Dept. Computer Science & Eng. University of Washington.
Bayesian Learning By Porchelvi Vijayakumar. Cognitive Science Current Problem: How do children learn and how do they get it right?
Ahsanul Haque *, Swarup Chandra *, Latifur Khan * and Michael Baron + * Department of Computer Science, University of Texas at Dallas + Department of Mathematical.
Artificial Intelligence And Machine learning. Drag picture to placeholder or click icon to add What is AI?
NEURAL NETWORKS FOR DATA MINING
第十讲 概率图模型导论 Chapter 10 Introduction to Probabilistic Graphical Models
Comparison of Bayesian Neural Networks with TMVA classifiers Richa Sharma, Vipin Bhatnagar Panjab University, Chandigarh India-CMS March, 2009 Meeting,
Machine Learning.
Reasoning in Uncertain Situations
Artificial Intelligence Course Overview Course By Sukchatri PRASOMSUK University of Phayao, ICT.
Genetic Algorithms Siddhartha K. Shakya School of Computing. The Robert Gordon University Aberdeen, UK
Markov Logic and Deep Networks Pedro Domingos Dept. of Computer Science & Eng. University of Washington.
1 2010/2011 Semester 2 Introduction: Chapter 1 ARTIFICIAL INTELLIGENCE.
Instructor: Pedro Domingos
CSE & CSE6002E - Soft Computing Winter Semester, 2011 Course Review.
Quiz Week 8 Topical. Topical Quiz (Section 2) What is the difference between Computer Vision and Computer Graphics What is the difference between Computer.
1 Relational Factor Graphs Lin Liao Joint work with Dieter Fox.
Markov Networks: Theory and Applications Ying Wu Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208
Progress Report ekker. Problem Definition In cases such as object recognition, we can not include all possible objects for training. So transfer learning.
Hierarchical Mixture of Experts Presented by Qi An Machine learning reading group Duke University 07/15/2005.
FNA/Spring CENG 562 – Machine Learning. FNA/Spring Contact information Instructor: Dr. Ferda N. Alpaslan
AI Overview Reference: "Artificial Intelligence, a Modern Approach, 3 rd ed."
A User-Guided Approach to Program Analysis Ravi Mangal, Xin Zhang, Mayur Naik Georgia Tech Aditya Nori Microsoft Research.
Pedro Domingos University of Washington. Evolution Experience Culture.
Chapter 12 Case Studies Part B. Control System Design.
1 Neural Networks MUMT 611 Philippe Zaborowski April 2005.
Who am I? Work in Probabilistic Machine Learning Like to teach 
Learning Deep Generative Models by Ruslan Salakhutdinov
Instructor: Pedro Domingos
Machine Learning for dotNET Developer Bahrudin Hrnjica, MVP
CSEP 546 Data Mining Machine Learning
Probabilistic Reasoning Over Time
CSEP 546 Data Mining Machine Learning
Basic Intro Tutorial on Machine Learning and Data Mining
Artificial Intelligence introduction(2)
CSE-490DF Robotics Capstone
CSE 515 Statistical Methods in Computer Science
CSEP 546 Data Mining Machine Learning
Evolutionist approach
Overview of Machine Learning
Artificial Intelligence 0. Course Overview
Future of Artificial Intelligence
Belief Networks CS121 – Winter 2003 Belief Networks.
Dan Roth Department of Computer Science
Artificial Intelligence Machine Learning
Presentation transcript:

Pedro Domingos University of Washington

Traditional Programming Machine Learning Computer Data Algorithm Output Computer Data Output Algorithm

Traditional Programming Machine Learning Computer Data Algorithm Output Master Algorithm Data Output Algorithm

TribeOriginsMaster Algorithm SymbolistsLogic, philosophyInverse deduction ConnectionistsNeuroscienceBackpropagation EvolutionariesEvolutionary biologyGenetic programming BayesiansStatisticsProbabilistic inference AnalogizersPsychologyKernel machines

Tom MitchellSteve MuggletonRoss Quinlan

AdditionSubtraction ――― = ? ―― 2 + ? ――― = 4 ――

Deduction Socrates is human + Humans are mortal. ――――――――――― = ? Induction Socrates is human + ? ――――――――――― = Socrates is mortal ――――――――――

Yann LeCunGeoff HintonYoshua Bengio

John Koza John HollandHod Lipson

David HeckermanJudea PearlMichael Jordan

Peter HartVladimir VapnikDouglas Hofstadter

TribeProblemSolution SymbolistsKnowledge compositionInverse deduction ConnectionistsCredit assignmentBackpropagation EvolutionariesStructure discoveryGenetic programming BayesiansUncertaintyProbabilistic inference AnalogizersSimilarityKernel machines

TribeProblemSolution SymbolistsKnowledge compositionInverse deduction ConnectionistsCredit assignmentBackpropagation EvolutionariesStructure discoveryGenetic programming BayesiansUncertaintyProbabilistic inference AnalogizersSimilarityKernel machines But what we really need is a single algorithm that solves all five!

Representation Probabilistic logic (e.g., Markov logic networks) Weighted formulas → Distribution over states Evaluation Posterior probability User-defined objective function Optimization Formula discovery: Genetic programming Weight learning: Backpropagation

Much remains to be done... We need your ideas

Home Robots Cancer Cures360 o Recommenders World Wide Brains