Re: The Emperor’s New Clothes [John Sowa] (Was Linear Algebraic Approaches to Logic Programming)

Whats also interesting, the recent physics
nobel price recipient Geoffrey Hinton has also
a like 30 year old paper about MoE,
which has like 6652 citations:
 > Adaptive Mixtures of Local Experts
 > https://www.cs.toronto.edu/~fritz/absps/jjnh91.pdf
Mild Shock schrieb:

 John Sowa shows clear signs of coping problems. We just
have an instance of “The Emperor’s New Clothes” some
companies have become naked with the advent of GPT,
 I don’t think it is productive to postulate
some CANNOT like here:
  > Linguists say that LLMs cannot be a language mode'.
 > - Tensors do not make the linguistic information explicit.
 > - They do not distinguish the syntax, sernantics, and ontology.
 > - GPT cannot use the 60• years of Al research and development.
 > https://www.youtube.com/watch?v=6K6F_zsQ264
 Then in the next slide he embraces tensors for
his new Prolog system nevertheless. WTF! Basically
this is a very narrow narrative, which is totally
 unfounded in my opinion. Just check out these papers:
 GRIN: GRadient-INformed MoE
[2409.12136] GRIN: GRadient-INformed MoE
https://arxiv.org/abs/2409.12136
 A Survey on Mixture of Experts
[2407.06204] A Survey on Mixture of Experts
https://arxiv.org/abs/2407.06204
 This paints a totally different picture of LLMs, seems
they are more in the tradition of CYC by Douglas Lenant.
 Mild Shock schrieb:

Hi,
>
Maybe one can get a better grip of an intimate
relationship, simply by some hands on?
>
Linear Algebraic Approaches to Logic Programming
>
Katsumi Inoue (National Institute of Informatics, Japan)
>
Abstract: Integration of symbolic reasoning and machine
learning is important for robust AI.  Realization of
symbolic reasoning based on algebraic methods is promising
to bridge between symbolic reasoning and machine learning,
since algebraic data structures have been used in machine
learning. To this end, Sakama, Inoue and Sato have defined
notable relations between logic programming and linear
algebra and have proposed algorithms to compute logic
programs numerically using tensors.  This work has been
extended in various ways, to compute supported and stable
models of normal logic programs, to enhance the efficiency
of computation using sparse methods, and to enable abduction
for abductive logic programming.  A common principle in
this approach is to formulate logical formulas as vectors/
matrices/tensors, and linear algebraic operations are
applied on these elements for computation of logic programming.
Partial evaluation can be realized in parallel and by self-multiplication, showing the potential for exponential
speedup.  Furthermore, the idea to represent logic programs
as tensors and matrices and to transform logical reasoning
to numeric computation can be the basis of the differentiable
methods for learning logic programs.
>
https://www.iclp24.utdallas.edu/invited-speakers/
>
Bye
>
Mild Shock schrieb:

Hi,
>
Ok this one is only 250 bucks for a TPU:
>
Introducing NVIDIA Jetson Orin™ Nano Super
https://www.youtube.com/watch?v=S9L2WGf1KrM
>
Now I am planning to do the following:
>
Create a tensor flow Domain Specific Language (DSL).
>
With these use cases:
>
- Run the tensor flow DSL locally in
   your Prolog system interpreted.
>
- Run the tensor flow DSL locally in
   your Prolog system compiled.
>
- Run the tensor flow DSL locally on
   your Tensor Processing Unit (TPU).
>
- Run the tensor flow DSL remotely
   on a compute server.
>
- What else?
>
Maybe also support some ONNX file format?
>
Bye

>