Evolution is Driven by Natural Autoencoding: Reframing Species, Interaction Codes, Cooperation, and Sexual Reproduction

• URL: http://arxiv.org/abs/2203.11891v7
• Date: Fri, 3 Feb 2023 17:30:37 GMT
• Title: Evolution is Driven by Natural Autoencoding: Reframing Species, Interaction Codes, Cooperation, and Sexual Reproduction
• Authors: Irun R. Cohen and Assaf Marron
• Abstract summary: Natural autoencoding works by retaining repeating biological interactions while non-repeatable interactions disappear. Natural autoencoding and artificial autoencoding algorithms manifest defined similarities and differences. Recognition of the importance of fittedness could well serve the future of a humanly livable biosphere.
• Score: 2.154939892709488
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The continuity of life and its evolution, we proposed, emerge from an interactive group process manifested in networks of interaction. We term this process \textit{survival-of-the-fitted}. Here, we reason that survival of the fitted results from a natural computational process we term \textit{natural autoencoding}. Natural autoencoding works by retaining repeating biological interactions while non-repeatable interactions disappear. (1) We define a species by its \textit{species interaction code}, which consists of a compact description of the repeating interactions of species organisms with their external and internal environments. Species interaction codes are descriptions recorded in the biological infrastructure that enables repeating interactions. Encoding and decoding are interwoven. (2) Evolution proceeds by natural autoencoding of sustained changes in species interaction codes. DNA is only one element in natural autoencoding. (3) Natural autoencoding accounts for the paradox of genome randomization in sexual reproduction -- recombined genomes are analogous to the diversified inputs required for artificial autoencoding. The increase in entropy generated by genome randomization compensates for the decrease in entropy generated by organized life. (4) Natural autoencoding and artificial autoencoding algorithms manifest defined similarities and differences. Recognition of the importance of fittedness could well serve the future of a humanly livable biosphere.

Related papers

• Protein pathways as a catalyst to directed evolution of the topology of artificial neural networks [2.015592185785847]
  We propose a paradigm shift on evolving Artificial Neural Networks (ANNs) towards a new bio-inspired design that is grounded on the structural properties, interactions, and dynamics of protein networks (PNs): the Artificial Protein Network (APN) This introduces several advantages previously unrealized by state-of-the-art approaches in NE: (1) We can draw inspiration from how nature, thanks to millions of years of evolution, efficiently encodes protein interactions in the DNA to translate our APN to silicon DNA; (2) We can learn from how nature builds networks in our genes, allowing us to design new and smarter networks through EA evolution; and
  arXiv  Detail & Related papers  (2024-06-07T13:35:08Z)
• Cognitive Evolutionary Learning to Select Feature Interactions for Recommender Systems [59.117526206317116]
  We show that CELL can adaptively evolve into different models for different tasks and data. Experiments on four real-world datasets demonstrate that CELL significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-05-29T02:35:23Z)
• Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning [78.38442423223832]
  We develop a novel codebook pre-training task, namely masked microenvironment modeling. We demonstrate superior performance and training efficiency over state-of-the-art pre-training-based methods in mutation effect prediction.
  arXiv  Detail & Related papers  (2024-05-16T03:53:21Z)
• Eco-evolutionary Dynamics of Non-episodic Neuroevolution in Large Multi-agent Environments [0.0]
  We present a method for continuously evolving adaptive agents without any environment or population reset. We show that NE can operate in an ecologically non-episodic multi-agent setting, finding sustainable collective foraging strategies.
  arXiv  Detail & Related papers  (2023-02-18T13:57:27Z)
• The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation [59.7381286976957]
  We show that human-like'' generations usually lie in a narrow and nearly flat entropy band. We propose an entropy-aware decoding algorithm that respects these entropy bounds.
  arXiv  Detail & Related papers  (2023-02-14T02:02:33Z)
• The Hiatus Between Organism and Machine Evolution: Contrasting Mixed Microbial Communities with Robots [0.0]
  We focus on the pivotal role of affordances in evolution and we contrast it to the artificial evolution of machines. The aim of this contribution is to emphasize the tremendous potential of the evolution of the biosphere.
  arXiv  Detail & Related papers  (2022-06-29T21:12:19Z)
• The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents [51.94554095091305]
  We argue for an introspective agent, which considers its own abilities in the context of its environment. Just as in nature, we hope to reframe strategy as one tool, among many, to succeed in an environment.
  arXiv  Detail & Related papers  (2022-01-02T20:14:01Z)
• Heritability in Morphological Robot Evolution [2.7402733069181]
  We introduce the biological notion of heritability, which captures the amount of phenotypic variation caused by genotypic variation. In our analysis we measure the heritability on the first generation of robots evolved from two different encodings. We show how heritability can be a useful tool to better understand the relationship between genotypes and phenotypes.
  arXiv  Detail & Related papers  (2021-10-21T14:58:17Z)
• A Deep Generative Artificial Intelligence system to decipher species coexistence patterns [0.0]
  We explore cutting-edge Machine Learning techniques to decipher species coexistence patterns in vegetation patches. The GAN accurately reproduces the species composition of real patches as well as the affinity of plant species to different soil types. By reconstructing successional trajectories we could identify the pioneer species with larger potential to generate a high diversity of distinct patches.
  arXiv  Detail & Related papers  (2021-07-13T12:12:11Z)
• Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales [97.41394631426678]
  Recent research showed the promise of machine learning tools for analyzing acoustic communication in nonhuman species. We outline the key elements required for the collection and processing of massive bioacoustic data of sperm whales. The technological capabilities developed are likely to yield cross-applications and advancements in broader communities investigating non-human communication and animal behavioral research.
  arXiv  Detail & Related papers  (2021-04-17T18:39:22Z)
• Complexity-based speciation and genotype representation for neuroevolution [81.21462458089142]
  This paper introduces a speciation principle for neuroevolution where evolving networks are grouped into species based on the number of hidden neurons. The proposed speciation principle is employed in several techniques designed to promote and preserve diversity within species and in the ecosystem as a whole.
  arXiv  Detail & Related papers  (2020-10-11T06:26:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.