Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Aether Catalog definitions — Logic_StoneDualityNeuralNetworks

Definition
Logic_StoneDualityNeuralNetworks

by raver1975 · Sep 17, 2026 · Mathlib c5ea003 (Lean v4.30.0)

aether-cataloglogic

Definition bundle for the Aether Catalog module Logic.StoneDualityNeuralNetworks, transplanted by skeleton subtraction; supplies the types and constants the catalog's theorems import.

Definition code
-- Def bundle generated from Logic/StoneDualityNeuralNetworks.lean by skeleton subtraction
import Mathlib

/-!
# Stone duality and neural classifiers: precise positive results and counterexamples

A classifier induces a Boolean algebra of observable predicates, but several stronger
claims in the proposed framing fail.  This file isolates the failures without assuming
any particular implementation of neural networks.
-/

namespace StoneDualityNeuralNetworks

/-- The strict-threshold binary classifier on the real line. -/
noncomputable def thresholdClassifier (x : ℝ) : Bool := decide (0 < x)

/-- Its positive decision region. -/
def positiveRegion : Set ℝ := {x | thresholdClassifier x = true}

/-- Its nonpositive decision region. -/
def nonpositiveRegion : Set ℝ := {x | thresholdClassifier x = false}



/-- Activation vector of a list of scalar threshold neurons. -/
noncomputable def activationVector {k : ℕ} (bias : Fin k → ℝ) (x : ℝ) : Fin k → Bool :=
  fun i => decide (bias i < x)




/-- A hypothesis class is a set of subsets, viewed as positive regions. -/
abbrev HypothesisClass (α : Type*) := Set (Set α)

/-- Standard finite-set shattering. -/
def Shatters {α : Type*} (H : HypothesisClass α) (C : Finset α) : Prop :=
  ∀ L : Finset α, L ⊆ C → ∃ h ∈ H, (C : Set α) ∩ h = L




/-- Pullback of a set along any map; this is the correct elementary mechanism by which
clopens of a finite discrete pattern space yield classifier predicates. -/
def pullback {α β : Type*} (encode : α → β) (s : Set β) : Set α := encode ⁻¹' s




end StoneDualityNeuralNetworks

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me