* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download The Five Tribes of Machine Learning And What You
Survey
Document related concepts
Lateral computing wikipedia , lookup
Factorization of polynomials over finite fields wikipedia , lookup
Algorithm characterizations wikipedia , lookup
Natural computing wikipedia , lookup
Machine learning wikipedia , lookup
Gene expression programming wikipedia , lookup
Expectation–maximization algorithm wikipedia , lookup
Stream processing wikipedia , lookup
Artificial intelligence wikipedia , lookup
Probabilistic context-free grammar wikipedia , lookup
Pattern recognition wikipedia , lookup
Theoretical computer science wikipedia , lookup
Transcript
Pedro Domingos University of Washington Evolution Culture Experience Evolution Experience Culture Computers 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 Traditional Programming Data Algorithm Computer Output Computer Algorithm Machine Learning Data Output 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 Tribe Origins Master Algorithm Symbolists Logic, philosophy Inverse deduction Connectionists Neuroscience Backpropagation Evolutionaries Evolutionary biology Genetic programming Bayesians Statistics Probabilistic inference Analogizers Psychology Kernel machines Tom Mitchell Steve Muggleton Ross Quinlan Addition Subtraction 2 + 2 ――― ―― = ? 2 + ? ――― ―― = 4 Deduction Induction Socrates is human + Humans are mortal . ――――――――――― ―――――――――― = ? Socrates is human + ? ―――――――――― ――――――――――― = Socrates is mortal Yann LeCun Geoff Hinton Yoshua Bengio John Koza John Holland Hod Lipson David Heckerman Judea Pearl Michael Jordan Peter Hart Vladimir Vapnik Douglas Hofstadter Tribe Problem Solution Symbolists Knowledge composition Inverse deduction Connectionists Credit assignment Backpropagation Evolutionaries Structure discovery Genetic programming Bayesians Uncertainty Probabilistic inference Analogizers Similarity Kernel machines Tribe Problem Solution Symbolists Knowledge composition Inverse deduction Connectionists Credit assignment Backpropagation Evolutionaries Structure discovery Genetic programming Bayesians Uncertainty Probabilistic inference Analogizers Similarity Kernel 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 World Wide Brains Cancer Cures 360o Recommenders 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.