Re: The future of KR in retrospective

Le jeu. 27 juin 2019 à 11:16, William Waites <wwaites@tardis.ed.ac.uk> a
écrit :

> Thank you for that article, Paola, it was very nice reading over first
> coffee.
>

Paola, Thanks for sharing that interesting article.

Explicit representation of knowledge is almost entirely absent in
> connectionist
> systems.


Are you sure? Isn't for instance word embedding relying on sequence of words
and as such take features from knowledge representation? Similarly, markov
models rely on the probability of appearance of a given "token". The token
can
encode both sense and grammatical features.


> But they work, and they echo the underlying biology.


Probably.



> A child doesn't learn by being fed a bunch of facts and rules, a child
> learns by example and
> a trial and error feedback loop.


Again, this doesn't expel rules or dynamic programming. Somehow I connect
logic to dynamic programming.


> First comes filtering out what is relevant and
> what is not relevant. Any kind of explicit reasoning comes later and never
> seems to stand on its own


I prefer to say that _verbal reasoning_ comes later.


> (this might be why mathematicians continue to speak
> of intuition both for finding and for understanding formal proofs).
>
> What is the relationship between what seems to be an underlying
> connectionist
> architecture and the explicit reasoning that seems to float on top of it?
> This is a burning question as more and more real-world decisions are made
> with the help of artificial neural networks but without giving the kind of
> explanation or insight that logic is good at providing.
>




> Brachman does mention "hybrid reasoning systems" but the conception seems
> more modular, consisting of specialised, domain-specific subsystems. Within
> the set of systems that are logic-based, that seems very sensible. Maybe
> the whole RDF programme is one such subsystem, and problems arise when it
> tries to be more general than it is. But the relationship between
> connectionist
> systems and logic-systems is not this kind of division of labour. They seem
> fundamentally different.
>


Different and complementary. My intuition is that logic and connectionist
approach
are what normal forms and aggregation are to relational database systems.
Logic is the source of truth whereas connectionist approach provides a
summary.



> Here is a wild conjecture. The relationship between connectionist models
> and
> logic models is roughly analogous to the relationship between discrete
> and continuous formulations of problems in mathematics and physics. If that
> is the case then the relationship should be described with a limit of some
> kind. In situations where logic falls down, where the reasons seem vague
> and ill-defined, this limit argument does not hold, we are not in
> continuous
> territory. When neural networks seem to lack explanatory power, it's
> because
> we are looking too closely at the details and don't have the approximate
> but clear and sharp picture given by logic.
>