An Initial Look at Self-Reprogramming Artificial Intelligence

04/30/2022
by   Alex Sheng, et al.
0

Rapid progress in deep learning research has greatly extended the capabilities of artificial intelligence technology. Conventional AI models are constrained to explicit human-designed algorithms, although a growing body of work in meta-learning, neural architecture search, and related approaches have explored algorithms that self-modify to some extent. In this paper, we develop and experimentally validate the first fully self-reprogramming AI system. Applying AI-based computer code generation to AI itself, we implement an algorithm with the ability to continuously modify and rewrite its own neural network source code.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/09/2019

Making AI meaningful again

Artificial intelligence (AI) research enjoyed an initial period of enthu...
research
10/25/2022

A Streamlit-based Artificial Intelligence Trust Platform for Next-Generation Wireless Networks

With the rapid development and integration of artificial intelligence (A...
research
12/13/2019

Does AlphaGo actually play Go? Concerning the State Space of Artificial Intelligence

The overarching goal of this paper is to develop a general model of the ...
research
06/04/2017

Brain Intelligence: Go Beyond Artificial Intelligence

Artificial intelligence (AI) is an important technology that supports da...
research
05/27/2019

AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence

Perhaps the most ambitious scientific quest in human history is the crea...
research
03/29/2021

Self-Constructing Neural Networks Through Random Mutation

The search for neural architecture is producing many of the most excitin...

Please sign up or login with your details

Forgot password? Click here to reset