#computationalrhetoric kết quả tìm kiếm

Computational interpretation (Curry–Howard): Propositions = types Proofs = programs A → B = function type A ∧ B = product type A ∨ B = sum type Intuitionistic semantics = type inhabitation semantics. Truth = definability.

Exactly! If we translate this understanding to things like poetry, scripture, slang, etc… it makes sense how we instantly understand (sometimes at deeper levels) concepts that if explained outright would get lost in translation. I modeled a framework for processing info based…

I would welcome @David_Gunkel’s take. But I don’t see “computational” here as a metaphor. I see it as structure-preserving evolution. "Clockwork" = rigid mechanism. Computational = rule-governed transformation, which can be adaptive, organic, quantum, even paradoxical.

Chatgpt taught me some fascinating technical grammar terms for the weird binary parallelism it uses all the time. “Copular clause (X is Y) combined with a contrastive, gnomic punchline.” This is a good flag for AI writing, btw, because humans don’t do it very often.

"The preemption of the tertiary protention is possible only because of the computational hermeneutics, which is essentially recursive: It constantly evaluates the past in order to anticipate the future, which in turn determines the present." -Yuk Hui (@digital_objects)

understand this - the final form of lethality as expressed by man is not warlikeness, barbarity, violence. it is to become a computer dedicated to a single task and purpose, it is to approach a synthetic environment of operators, data and parsing. we are here now

instead of a chain-of-thought that is purely text: <think> word → word → word </think> CoVT uses: <think> word → visual-latent → word → visual-latent → ... </think>

This axiom implies a radical revision of cognitive architecture. Space, meaning, and even the perception of time are not pre-existing containers for thought but are dimensions actively generated by relational processes. The more coherent the relationship between patterns, the…

You are making a fundamental category error: mistaking Syntax for Semantics. Computation is the manipulation of symbols according to rules, but thinking is the understanding of what those symbols mean. A computer can process the word "grief" perfectly, it can define it, use it,…

From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought paper page: huggingface.co/papers/2306.12… How does language inform our downstream thinking? In particular, how do humans make meaning from language -- and how can we leverage…

Humans write human readable code. It gets compiled into non human readable bytecode. It gets executed by a virtual machine then a CPU. At no point does the math really know or care what the humans are calling it. Math is the math. Words are to help the humans understand it all.

People find the sentence "my artificial neural network is sentient" vastly more plausible than the sentence "my matrix multiplication algorithm is sentient" even though they are roughly the same claim. This implies to me that "neural network" is bad terminology.

The computational theory of mind is wrong, and that’s as good a way of any as saying that gender identity is fake

In case you ever wondered why @ridolfoj who worked on #RhetoricalVelocity and I, with work on #computationalrhetoric, thought we should ring the bell about #rhetops...

Very good (thoughtful, insightful, reproducable) #computationalrhetoric by @easyrhetor !

Mathematical Reasoning in Latent Space openreview.net/forum?id=Ske31… will be featured at #iclr2020. Multiple step reasoning can be performed on embedding vectors of mathematical formulas.

Computational trinity: ncatlab.org/nlab/show/comp… is a tripartite correspondence between Logic, Type Theory, and Category Theory. Here's a mnemonic visualization that illustrates it as a computational object projecting shadows in 3 orthogonal dimensions.

Approximate mathematical reasoning is possible in the latent space alone. We created semantic embedding of formulas and performed complicated multi-step reasoning on them, then we compared it with the symbolic results: arxiv.org/pdf/1909.11851…

Practical Grammar-based Procedural Modeling of Architecture [pdf] research.michael-schwarz.com/publ/files/pro… #procgen

Today at #sigdoc17 @OmizoRM will present our latest #computationalrhetoric work - cool theoretical stuff on text viz! @msuwide

Currently making-- #computationalrhetoric #MATRIX_MSU #WIDE_MATRIX