Files
website/content/research/2021-03-06-tasked-self-replication.mdx
Steffen Illium 0444067c2d
Some checks failed
Next.js App CI / docker (push) Failing after 3m19s
refined design
2025-09-14 22:49:23 +02:00

35 lines
2.6 KiB
Plaintext

---
title: "Tasked Self-Replication"
tags: [artificial-life, complex-systems, neural-networks, self-organization, multi-task-learning, self-replication, artificial-chemistry, evolution, computational-systems, guided-evolution, artificial-intelligence]
excerpt: "Self-replicating networks perform tasks, exploring stabilization in artificial chemistry."
teaser: "/figures/13_sr_teaser.jpg"
venue: "ALIFE 2021"
---
Building upon the concept of self-replicating neural networks <Cite bibtexKey="gabor2019self" />, this research explores the integration of **auxiliary functional goals** alongside the primary objective of self-replication. The aim is to create networks that can not only reproduce their own weights but also perform useful computations or interact meaningfully with an environment simultaneously.
<CenteredImage
src="/figures/13_sr_analysis.jpg"
alt="Analysis graphs or visualizations related to dual-task self-replicating networks"
width={800}
height={600}
caption="Analysis of networks balancing self-replication and auxiliary tasks."
/>
The study introduces a methodology for **dual-task training**, utilizing distinct input/output vectors to manage both the replication process and the execution of a secondary task. A key finding is that the presence of an auxiliary task does not necessarily hinder self-replication; instead, it can sometimes **complement and even stabilize** the replication dynamics.
<FloatingImage
src="/figures/13_sr_recovering.png"
alt="3D plot showing trajectories of network states over timesteps with starting and ending points"
width={400}
height={400}
float="right"
caption="Visualization of network state trajectories and recovery in a transformed 3D space over timesteps, illustrating dynamic evolution."
/>
Further investigations were conducted within the framework of an **"artificial chemistry" environment**, where populations of these dual-task networks interact:
* The impact of varying **action parameters** (related to the secondary task) on the collective learning or emergent behavior of the network population was examined.
* A concept of a specially designed **"guiding particle"** network was introduced. This network influences its peers, demonstrating a mechanism for potentially steering the population's evolution towards desired goal-oriented behaviors.
This work provides insights into how functional complexity can be integrated with self-replication in computational systems, offering potential pathways for developing more sophisticated artificial life models and exploring guided evolution within network populations. <Cite bibtexKey="gabor2021goals" />