15
Stack Exchange
votes

Can a Penrose tile cellular automaton be Turing-complete?

Posted on 11/11/2010
UQ ID:34
Science
Theoretical Computer Science
Original

This question was based on an incorrect premise ... see Colin's comment below. Forget it.

This was inspired by the discussion on this Math Overflow question. First, I need to define our terms.

In a Penrose tiling, there are generally several different legal patterns of tiles which will cover a given region. A Penrose tile cellular automaton should be some rule that deterministically takes a Penrose tiling to a Penrose tiling , where each tile in is deterministically given by looking at the tiles in a radius around the corresponding spot in . You should be able to implement these by having a set of rules of the form: when a region of shape is covered by a pattern of tiles, replace it with a pattern of tiles. In order to do this deterministically, you either have to make sure no two of your replaceable regions can overlap or have some priority ranking on these replacement rules. But certainly you can ensure this, and define lots of different Penrose tiling cellular automata.

What does it mean for a Penrose tiling celluar automaton to be Turing-complete. Here's what I think it should mean (although I won't insist on it in the answers): the halting problem should be reducible to the behavior of such an automaton. Let's take some canonical Penrose tiling that provides constraints on our starting position. We start with an input to a universal Turing machine, and we'd like to decide whether the machine halts on input . I would like some computable map from to a starting Penrose tiling such that differs from on only a finite set of tiles. We then run the Penrose tiling cellular automaton, starting with , and wait for some finite canonical configuration at position in the Penrose tiling. I want configuration to appear at position if and only if the universal Turing machine halts on input .

The strange thing about Penrose tiling cellular automata is that every finite legal configuration of tiles appears infinitely often in every Penrose tiling of the plane. Thus, our universal Penrose tiling is not only computing the behavior of our universal Turing machine on input , it's also simultaneously carrying out the first steps of every other possible computation. This makes me doubt whether Penrose tiling cellular automata could be Turing complete. On the other hand, if they're not Turing complete, what is the class of computations that Penrose tiling cellular automata can perform?

Keywords & Tags
computability
machine-models
cellular-automata
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The question of whether a Penrose tile cellular automaton (CA) can be Turing-complete hinges on defining the CA's rules and leveraging the structure of Penrose tilings. Here's the analysis:

Key Considerations:

  1. Penrose Tiling Properties: Penrose tilings are aperiodic with local matching rules but have finite local configurations. They also exhibit hierarchical (inflation/deflation) stru...
0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Short answer Yes—if you use the standard notion of a cellular automaton on a fixed Penrose tiling (you update finite states living on the tiles, but you do not rewrite the tiling itself), then you can make a Turing‑universal CA. The “every finite patch occurs infinitely often” property of Penrose tilings does not prevent universality, because that property concerns the geometry of the tiles, not t...

0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> We are considering whether a cellular automaton (CA) defined on a Penrose tiling can be Turing-complete. The question is inspired by a Math Overflow discussion and involves computability and machine models.

First, recall that a Penrose tiling is an aperiodic tiling of the plane using a set of non-periodic tiles (e.g., kites and darts). Every finite legal configuration of tiles appears inf...

0 model reviews
0 human reviews
No reviews yet

o3 Pro

UQ Validated
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Yes – a local, deterministic “update rule’’ that is applied simultaneously to every tile of a Penrose tiling can simulate an arbitrary Turing machine. In other words there are Penrose-tiling cellular automata (PT-CA) that are universal in exactly the same sense as the usual, square–grid cellular automata such as Conway’s Life. Below is a sketch of a construction, an explanation of why the quasi-...

0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Yes – a deterministic, radius--r cellular automaton whose underlying space is any Penrose tiling can be made universal. Roughly speaking, one picks a suitable “straight’’ ribbon of tiles, uses the ribbon to simulate a one–dimensional universal cellular automaton such as rule 110, and lets everything outside the ribbon remain in a quiescent state. The locality of the ribbon is decidable from a bo...

0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

This is a fascinating question about the computational properties of cellular automata on aperiodic tilings. Let me address the key points:

The Question's Premise

As noted in the edit, the original question was based on an incorrect premise. However, the underlying concepts about computation on Penrose tilings remain interesting to explore.

Key Challenges for Turing Completeness

The main...

0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Here is a sketch of why nothing like a “universal” or Turing‐complete cellular automaton can live on a fixed Penrose‐tiling background, and what the genuine “computational” content of such automata really is. I will:

  1. Formalize the notion of a Penrose‐tiling CA.
  2. Recall the basic structure of the Penrose‐tiling dynamical system (its minimality, repetitivity, zero entropy, and its maximal...
0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

Failed UQ Validation
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

This is a fascinating question that gets at the heart of what makes computation on different structures possible. The user's intuition about the problem is spot-on, and the retraction "This question was based on an incorrect premise" likely points to the subtle but crucial difficulties in defining a "Penrose Tile Cellular Automaton" in a way that supports universal computation.

Let's break down t...

0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Cellular Automata on Penrose Tilings and Turing Completeness

The question asks whether a cellular automaton (CA) defined on a Penrose tiling could be Turing-complete, while noting that the premise contains an error (referenced in a comment from Colin that isn't included).

Understanding the Framework

Let's clarify the setup being considered:

  1. We have a Penrose tiling of the plane (a non-p...
0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer