Selfconstructing Neural Networks Through Random Mutation
ASecurity
**arXiv ID:** 2103.15692 **Authors:** Samuel Schmidgall **Published:** 2021-03-29T15:27:38Z **Abstract:** The search for neural architecture is producing many of the most exciting results in artificial intelligence. It has increasingly become apparent that task-specific neural architecture plays a crucial role for effectively solving problems. This paper presents a simple method for learning neural architecture through random mutation. This method demonstrates 1) neural architecture may be le...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Selfconstructing Neural Networks Through Random Mutation?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-selfconstructing-neural-networks-through-random-mu)
# Self-Constructing Neural Networks Through Random Mutation
**arXiv ID:** 2103.15692
**Authors:** Samuel Schmidgall
**Published:** 2021-03-29T15:27:38Z
**Abstract:**
The search for neural architecture is producing many of the most exciting results in artificial intelligence. It has increasingly become apparent that task-specific neural architecture plays a crucial role for effectively solving problems. This paper presents a simple method for learning neural architecture through random mutation. This method demonstrates 1) neural architecture may be learned during the agent's lifetime, 2) neural architecture may be constructed over a single lifetime without any initial connections or neurons, and 3) architectural modifications enable rapid adaptation to dynamic and novel task scenarios. Starting without any neurons or connections, this method constructs a neural architecture capable of high-performance on several tasks. The lifelong learning capabilities of this method are demonstrated in an environment without episodic resets, even learning with constantly changing morphology, limb disablement, and changing task goals all without losing locomotion capabilities.
## Skill Description
This skill is generated from the arXiv paper: Self-Constructing Neural Networks Through Random Mutation (2103.15692).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2103.15692](http://arxiv.org/abs/2103.15692v1)
