Self-Constructing Neural Networks Through Random Mutation

03/29/2021
by   Samuel Schmidgall, et al.
1

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.

READ FULL TEXT
research
05/15/2022

Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning

Recently, Neural Architecture Search (NAS) methods have been introduced ...
research
10/04/2021

Max and Coincidence Neurons in Neural Networks

Network design has been a central topic in machine learning. Large amoun...
research
07/03/2023

Neural Architecture Transfer 2: A Paradigm for Improving Efficiency in Multi-Objective Neural Architecture Search

Deep learning is increasingly impacting various aspects of contemporary ...
research
04/30/2022

An Initial Look at Self-Reprogramming Artificial Intelligence

Rapid progress in deep learning research has greatly extended the capabi...
research
08/23/2018

Exploring Shared Structures and Hierarchies for Multiple NLP Tasks

Designing shared neural architecture plays an important role in multi-ta...
research
12/28/2017

Rapid Adaptation with Conditionally Shifted Neurons

We describe a mechanism by which artificial neural networks can learn ra...
research
12/28/2017

Learning Rapid-Temporal Adaptations

A hallmark of human intelligence and cognition is its flexibility. One o...

Please sign up or login with your details

Forgot password? Click here to reset