AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms

09/17/2017
by   Kory Becker, et al.
0

In this paper, we present the first-of-its-kind machine learning (ML) system, called AI Programmer, that can automatically generate full software programs requiring only minimal human guidance. At its core, AI Programmer uses genetic algorithms (GA) coupled with a tightly constrained programming language that minimizes the overhead of its ML search space. Part of AI Programmer's novelty stems from (i) its unique system design, including an embedded, hand-crafted interpreter for efficiency and security and (ii) its augmentation of GAs to include instruction-gene randomization bindings and programming language-specific genome construction and elimination techniques. We provide a detailed examination of AI Programmer's system design, several examples detailing how the system works, and experimental data demonstrating its software generation capabilities and performance using only mainstream CPUs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/09/2022

Supporting AI/ML Security Workers through an Adversarial Techniques, Tools, and Common Knowledge (AI/ML ATT CK) Framework

This paper focuses on supporting AI/ML Security Workers – professionals ...
research
11/13/2019

Zoea – Composable Inductive Programming Without Limits

Automatic generation of software from some form of specification has bee...
research
03/06/2022

Enabling Automated Machine Learning for Model-Driven AI Engineering

Developing smart software services requires both Software Engineering an...
research
10/01/2018

SmartChoices: Hybridizing Programming and Machine Learning

We present SmartChoices, an approach to making machine learning (ML) a f...
research
03/20/2018

The Three Pillars of Machine-Based Programming

In this position paper, we describe our vision of the future of machine-...
research
10/15/2021

GaussED: A Probabilistic Programming Language for Sequential Experimental Design

Sequential algorithms are popular for experimental design, enabling emul...
research
09/14/2023

WASM-MUTATE: Fast and Effective Binary Diversification for WebAssembly

WebAssembly has is renowned for its efficiency and security in browser e...

Please sign up or login with your details

Forgot password? Click here to reset