Evolution is Driven by Natural Autoencoding: Reframing Species, Interaction Codes, Cooperation, and Sexual Reproduction
March 22, 2022 ยท Declared Dead ยท ๐ Proceedings of the Royal Society B
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Irun R. Cohen, Assaf Marron
arXiv ID
2203.11891
Category
cs.NE: Neural & Evolutionary
Citations
13
Venue
Proceedings of the Royal Society B
Last Checked
4 months ago
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.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Neural & Evolutionary
๐ฎ
๐ฎ
The Ethereal
R.I.P.
๐ป
Ghosted
Deep Learning using Rectified Linear Units (ReLU)
R.I.P.
๐ป
Ghosted
Generative Adversarial Text to Image Synthesis
R.I.P.
๐ป
Ghosted
Regularized Evolution for Image Classifier Architecture Search
R.I.P.
๐ป
Ghosted
Temporal Ensembling for Semi-Supervised Learning
๐
๐
Old Age
Learning Structured Sparsity in Deep Neural Networks
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
๐ป
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
๐ป
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
๐ป
Ghosted