IJCAI 16 keynote on the need to bring modern AI accomplishments of recent years into connection with the more traditional goals of symbolic AI (and vice versa).

1. Tetherless World Constellation, RPI
KR in the age of
Deep Learning,
Watson,
and the Semantic Web
Jim Hendler
Tetherless World Professor of Computer, Web and Cognitive Sciences
Director, Institute for Data Exploration and Applications
Rensselaer Polytechnic Institute
http://www.cs.rpi.edu/~hendler
@jahendler (twitter)
Major talks at: http://www.slideshare.net/jahendler

2. Tetherless World Constellation, RPI
But first, Why the Moose?
This moose gave a keynote
with Tim Berners-Lee.
This moose gave a keynote
with Peter Norvig.

3. Tetherless World Constellation, RPI
Talk derives in large part from working on
forthcoming book
(More info at Springer booth)
(Thanks Alice!)

4. Tetherless World Constellation, RPI
Outline
• Several important AI technologies have
moved through “knees in the curve”
bringing much of the attention to AI again
– Deep Learning (& ML in general)
– Watson (& “cognitive computing”)
– Semantic Web (& the knowledge graph)
• But what about KR
– What it is, why it still matters
• And how can these come together
– Which comes with a lot of important challenges

5. Tetherless World Constellation, RPI
A) Deep Learning
“phase transition” in capabilities of neural networks
w/machine power

6. Tetherless World Constellation, RPI
Trained on lots of categorized images
Imagenet: Duck Imagenet: Cat

7. Tetherless World Constellation, RPI
Impressive results
Increasingly powerful techniques have yielded
incredible results in the past few years

8. Tetherless World Constellation, RPI
B) Watson

9. Tetherless World Constellation, RPI
The Watson DeepQA Pipeline

10. Tetherless World Constellation, RPI
Watson is based on ”Associative knowledge”
© IBM, used with permission.

11. Tetherless World Constellation, RPI
Impressive Results
Watson showed the power of “associative knowledge”

12. Tetherless World Constellation, RPI
C) Semantic Web

13. Tetherless World Constellation, RPI
From Semantic Web to the Knowledge Graph

14. Tetherless World Constellation, RPI
Based on a large “knowledge graph” mined from
extracted and learned data

15. Tetherless World Constellation, RPI
Many intermediate steps
(P. Norvig, WWW 2016, 4/16)

16. Tetherless World Constellation, RPI
Impressive results
Google finds embedded metadata on >30% of its crawl – Guha, 2015
Google “knowledge vault” reported to have over 1.6 billion “facts” (links)

17. Tetherless World Constellation, RPI
Summary: AI has done some way cool stuff
Summary (simplifying tremendously)
• Deep Learning: neural learning from data with high
quality, but imperfect results
• Watson: Associative learning from data with high
quality but imperfect results
• Semantic Web/Knowledge Graph: Graph links
formation from extraction, clustering and learning
As much as many of us “GOFAI” folks wish it, this stuff
cannot be ignored
but, there are still problems…

18. Tetherless World Constellation, RPI
Why did knowledge graph need
“”Human Judgments”?
Association ≠ Correctness

19. Tetherless World Constellation, RPI
Quick quiz
Who did this moose give invited talks with?
A) Stuart Russell & Vint Cerf
B) A deer and a keynote
C) IJCAI-16 and Alces Alces
D) Tim Berners-Lee and Peter Norvig

20. Tetherless World Constellation, RPI
Associational learning cannot
explain learning by “symbolic communication”
Who did this moose give invited talks with?
A) Stuart Russell & Vint Cerf (highly associated with target answer)
B) A deer and a keynote (word embedding similarity to question)
C) IJCAI-16 and Alces Alces (perceptually linked)
D) Tim Berners-Lee and Peter Norvig (Correct answer is
something most of you learned today, 1-shot, via being told)

21. Tetherless World Constellation, RPI
GOFAI: Knowledge Representation?
• A knowledge representation (KR) is most fundamentally a surrogate, a
substitute for the thing itself, used to enable an entity to
determine consequences by thinking rather than acting, i.e., by
reasoning about the world rather than taking action in it.
• It is a set of ontological commitments, i.e., an answer to the question: In
what terms should I think about the world?
• It is a fragmentary theory of intelligent reasoning, expressed in terms of
three components: (i) the representation's fundamental conception of
intelligent reasoning; (ii) the set of inferences the representation
sanctions; and (iii) the set of inferences it recommends.
• It is a medium for pragmatically efficient computation, i.e., the
computational environment in which thinking is accomplished. One
contribution to this pragmatic efficiency is supplied by the guidance a
representation provides for organizing information so as to facilitate
making the recommended inferences.
• It is a medium of human expression, i.e., a language in which we
say things about the world.
R. Davis, H. Shrobe, P. Szolovits (1993)

22. Tetherless World Constellation, RPI
KR: Human Expression
Cute kid story: first two words

23. Tetherless World Constellation, RPI
Telling cats from ducks doesn’t need KR
!

24. Tetherless World Constellation, RPI
“Saying things about the world” does
"If I was telling it to a
kid, I'd probably say
something like 'the cat
has fur and four legs and
goes meow, the duck is a
bird and it swims and
goes quack’. "
How would you explain the difference between a
duck and a cat to a child?
Woof

25. Tetherless World Constellation, RPI
KR: Surrogate knowledge?
Which could you sit in?
What is most likely to bite what?
Which one is most likely to become a computer
scientist someday?
…

26. Tetherless World Constellation, RPI
“Surrogate” knowledge
Which could you sit in?
What is most likely to bite what?
Which one is most likely to become a computer
scientist someday?
How would they go about doing it?

27. Tetherless World Constellation, RPI
KR: Recommended vs. Possible inference
Which one would you save if the house was on fire?

28. Tetherless World Constellation, RPI
Recommended vs. Possible inference
Which one would you save if the house was on fire?
Would you use a robot baby-sitter
without knowing which of the three
possibilities it would choose?

29. Tetherless World Constellation, RPI
KR systems in AI need grounded symbols
• Logic- and rule- based systems
– Ground in “model theory” with a notion of truth
and falsity
• Probabilistic Reasoning
– P(A|B) requires A, B map to “meaningful”
concepts, P to be a “real” probability
• Constraint Satisfaction, etc
– Finding an interpretation satisfying a set of
boolean (T,F) constraints
(Note: Yes, I am simplifying, blurring distinctions, ignoring
much cutting edge work… happy to discuss later)

30. Tetherless World Constellation, RPI
The challenge
• If we want to implement KR systems
on top of neural and associative
learners we have an issue
– The numbers coming out of Deep
Learning and Associative graphs are not
probabilities
– They don’t necessarily ground in
human-meaningful symbols
• ”sub-symbolic” learning …
• Association by clustering …
• Errorful extraction …

31. Tetherless World Constellation, RPI
The challenges
• Can we avoid throwing out the
reasoning baby with the grounding
bathwater?
– We still need planning systems
– We still want to be able to define the
rules that a system should follow
– We want to be able to interact with and
understand these systems
• Even if computers don’t need to be symbolic
communicators, WE DO!!!

32. Tetherless World Constellation, RPI
Not just “theory” the applications driving
much modern AI require new grounding ideas
Guruduth Banavar, w/permission)

33. Tetherless World Constellation, RPI
Starting Place: Rethinking grounding
– Formal Explanation vs. post hoc
justification
• Eg. Even if we cannot use a formal
decomposition to explain the reasoning, can
we produce a justification that explains it
– Reasoning systems that “know” some of
their axioms may be simply wrong
• Eg.F1 of .9 doesn’t mean answers are 90%
correct, it is (simplifying) more like 9 out of
10 answers are right, the others aren’t.
– Nailing context …

34. Tetherless World Constellation, RPI
Human-Aware AI
• Context is key
– AI systems still perform best in well-
defined contexts (or trained situations,
or where their document set is
complete, etc.)
– Humans are good at recognizing context
and deciding when extraneous factors
don’t make sense
• Extreme example: Stanislav Yevgrafovich
Petrov (the man who saved the world)

35. Tetherless World Constellation, RPI
Why this REALLY matters
• Humanity faces huges challenges
– eg. Our knowledge of cancer genomics
is being outpaced by mutations as
cancer continues to spread
– eg. Our neighborhoods degrade as
wealth disparity grows
– eg. Our climate warms as we argue
about the causes without changing
behaviors

36. Tetherless World Constellation, RPI
Attacking these problems require the best minds we have working
together: Human and AI!
The existential threat is not AI,
it’s not utilizing the AI we have correctly

37. Tetherless World Constellation, RPI
Summary of talk (minus moose)
• Modern AI is making some huge strides
– Eg. DL, Associative Learning, Knowledge
Graphs, …
• But the need for KR has not gone away
– Eg. Surrogacy, Recommended Inference,
Human communication
• The integration challenge will require
goring some sacred cows
– Grounding, explanation, context ….
• But we need to do it.

38. Tetherless World Constellation, RPI
Questions?