Corpus ID: 237940137

Self-Replicating Neural Programs

  title={Self-Replicating Neural Programs},
  author={Samuel Schmidgall},
In this work, a neural network is trained to replicate the code that trains it using only its own output as input. A paradigm for evolutionary self-replication in neural programs is introduced, where program parameters are mutated, and the ability for the program to more efficiently train itself leads to greater reproductive success. This evolutionary paradigm is demonstrated to produce more efficient learning in organisms from a setting without any explicit guidance, solely based on natural… Expand

Figures from this paper


Neural Network Quine
It is suggested that a self-replication mechanism for artificial intelligence is useful because it introduces the possibility of continual improvement through natural selection. Expand
Evolutionary Self-Replication as a Mechanism for Producing Artificial Intelligence
In this work, self-replication is explored as a mechanism for the emergence of intelligent behavior in modern learning environments and evolved organisms are shown to produce meaningful, complex, and intelligent behavior. Expand
Spontaneous Emergence of Self-Replicating and Evolutionarily Self-Improving Computer Programs
This chapter reports on the spontaneous emergence of computer programs exhibiting the ability to asexually reproduce, to reproduce by combining parts from two parents, and to improve theirExpand
Evolution , Ecology and Optimization of Digital Organisms
Digital organisms have been synthesized based on a computer metaphor of organic life in which CPU time is the “energy” resource and memory is the “material” resource. Memory is organized intoExpand
Self-Replicating Structures: Evolution, Emergence, and Computation
Recent studies showing that self-replicating structures can emerge from nonreplicating components, and that genetic algorithms can be applied to program automatically simple but arbitrary structures to replicate are discussed. Expand
Genome complexity, robustness and genetic interactions in digital organisms
The findings support the view that interactions are a general feature of genetic systems and the complex organisms are more robust than the simple ones with respect to the average effects of single mutations. Expand
Avida: Evolution Experiments with Self-Replicating Computer Programs
This chapter explains the general principles on which Avida is built, its main components and their interactions, and gives an overview of some prior research with Avida. Expand
The evolutionary origin of complex features
Findings show how complex functions can originate by random mutation and natural selection. Expand
Evolution of digital organisms at high mutation rates leads to survival of the flattest
According to quasi-species theory, selection favours the cloud of genotypes, interconnected by mutation, whose average replication rate is highest, and this prediction is confirmed using digital organisms that self-replicate, mutate and evolve. Expand
Cellular Automata Models of Self-Replicating Systems
The historical development of work on artificial self-replicating structures in cellular spaces is summarized, some recent advances are described, and genetic algorithms can be applied to automatically program simple but arbitrary structures to replicate. Expand