Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
And What You Can
Take from Each
Pedro Domingos
University of Washington
Evolution Experience
Culture
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 ...
1. Fill in gaps in existing knowledge
2. Emulate the brain
3. Simulate evolution
4. Systematically reduce uncertainty
5. N...
Tribe Origins Master Algorithm
Symbolists Logic, philosophy Inverse deduction
Connectionists Neuroscience Backpropagation
...
Tom Mitchell Steve Muggleton Ross Quinlan
Addition Subtraction
2
+ 2
―――
= ?
――
2
+ ?
―――
= 4
――
Deduction
Socrates is human
+ Humans are mortal .
―――――――――――
= ?
Induction
Socrates is human
+ ?
―――――――――――
= Socrates i...
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...
Tribe Problem Solution
Symbolists Knowledge composition Inverse deduction
Connectionists Credit assignment Backpropagation...
Representation
Probabilistic logic (e.g., Markov logic networks)
Weighted formulas → Distribution over states
Evaluation
P...
Much remains to be done . . .
We need your ideas
Home Robots
Cancer Cures 360o Recommenders
World Wide Brains
If we used all our technology resources,
we could actually give people personalized
recommendations for every step of your...
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15
Upcoming SlideShare
Loading in …5
×

Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

13,471 views

Published on

The Five Tribes of Machine Learning, and What You Can Take from Each: There are five main schools of thought in machine learning, and each has its own master algorithm – a general-purpose learner that can in principle be applied to any domain. The symbolists have inverse deduction, the connectionists have backpropagation, the evolutionaries have genetic programming, the Bayesians have probabilistic inference, and the analogizers have support vector machines. What we really need, however, is a single algorithm combining the key features of all of them. In this talk I will describe my work toward this goal, including in particular Markov logic networks, and speculate on the new applications that such a universal learner will enable, and how society will change as a result.

Published in: Technology

Pedro Domingos, Professor, University of Washington at MLconf ATL - 9/18/15

  1. 1. And What You Can Take from Each Pedro Domingos University of Washington
  2. 2. Evolution Experience Culture
  3. 3. Evolution Experience Culture Computers
  4. 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. 5. 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
  6. 6. 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
  7. 7. Tom Mitchell Steve Muggleton Ross Quinlan
  8. 8. Addition Subtraction 2 + 2 ――― = ? ―― 2 + ? ――― = 4 ――
  9. 9. Deduction Socrates is human + Humans are mortal . ――――――――――― = ? Induction Socrates is human + ? ――――――――――― = Socrates is mortal ―――――――――― ――――――――――
  10. 10. Yann LeCun Geoff Hinton Yoshua Bengio
  11. 11. John Koza John Holland Hod Lipson
  12. 12. David Heckerman Judea Pearl Michael Jordan
  13. 13. Peter Hart Vladimir Vapnik Douglas Hofstadter
  14. 14. 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
  15. 15. 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!
  16. 16. 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
  17. 17. Much remains to be done . . . We need your ideas
  18. 18. Home Robots Cancer Cures 360o Recommenders World Wide Brains
  19. 19. 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.

×