1. Pedro Domingos University of Washington

2. Evolution Experience Culture

3. Evolution Experience CultureComputers

4. Most of the knowledge in the world in the future is going to be extracted by machines and will reside in machines. – Yann LeCun, Director of AI Research, Facebook

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

6. 1. Fill in gaps in existing knowledge 2. Emulate the brain 3. Simulate evolution 4. Systematically reduce uncertainty 5. Notice similarities between old and new

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

8. Tom MitchellSteve MuggletonRoss Quinlan

9. AdditionSubtraction 2 + 2 ――― = ? ―― 2 + ? ――― = 4 ――

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

12. Yann LeCunGeoff HintonYoshua Bengio

17. John Koza John HollandHod Lipson

21. David HeckermanJudea PearlMichael Jordan

25. Peter HartVladimir VapnikDouglas Hofstadter

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

30. 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!

31. 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

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

33. Home Robots Cancer Cures360 o Recommenders World Wide Brains

34. If we used all our technology resources, we could actually give people personalized recommendations for every step of your life. – Aneesh Chopra, former CTO of the U.S.