Alien Coding

01/27/2023
by   Thibault Gauthier, et al.
0

We introduce a self-learning algorithm for synthesizing programs for OEIS sequences. The algorithm starts from scratch initially generating programs at random. Then it runs many iterations of a self-learning loop that interleaves (i) training neural machine translation to learn the correspondence between sequences and the programs discovered so far, and (ii) proposing many new programs for each OEIS sequence by the trained neural machine translator. The algorithm discovers on its own programs for more than 78000 OEIS sequences, sometimes developing unusual programming methods. We analyze its behavior and the invented programs in several experiments.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/18/2019

A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL

The sequence-to-sequence (seq2seq) model for neural machine translation ...
research
02/24/2022

Learning Program Synthesis for Integer Sequences from Scratch

We present a self-learning approach for synthesizing programs from integ...
research
07/08/2021

Using CollGram to Compare Formulaic Language in Human and Neural Machine Translation

A comparison of formulaic sequences in human and neural machine translat...
research
06/01/2017

NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems

In this paper, we present nmtpy, a flexible Python toolkit based on Thea...
research
04/01/2018

Marian: Fast Neural Machine Translation in C++

We present Marian, an efficient and self-contained Neural Machine Transl...
research
09/14/2022

Limit Cycles of AdaBoost

The iterative weight update for the AdaBoost machine learning algorithm ...
research
10/11/2021

Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching

We study the problem of synthesizing programs that include machine learn...

Please sign up or login with your details

Forgot password? Click here to reset