ARC prize: a call to arms for Genetic Programming by Alberto Tonda

The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to be easy to solve for humans and next to impossible for machine learning techniques which rely upon massive training data sets, like Deep Learning. Google's François Chollet, the author,  presents ARC as an attempt to push for AI algorithms able to "learn like humans" [1], or in other words, able to solve tasks after seeing just a small number of training instances, exploiting innate capacities to reason on geometry and number [2]. Just a few weeks ago, Chollet announced a Kaggle challenge on ARC, with a prize of 1 million $ [3] and a first deadline in November 2024, although submissions are already open [4].

I am not affiliated with the prize in any way, but I think this could represent a valuable opportunity for the GP/EA community: the tasks in ARC can be solved through *program synthesis*, as stated by Chollet himself [5], a function GP excels at; and the capacity of learning from a few samples is another strong suite of GP. Not to mention, just participating in the contest and comparing against other approaches could lead to cross-fertilization of new ideas, and even help promote GP as a robust AI alternative to the now more prominent DL approaches.

After discussing with colleagues, I decided to spread the news far and wide, in the hope that more and more people from our community would decide to take up the challenge. The current state of the art performance on ARC is still low (less than 40% accuracy on test at the time of writing), so the entry barriers should not be that high: now it's a good moment for GP researchers to take on the world and test our mettle!

[1] https://arxiv.org/pdf/1911.01547 

[2] https://aiguide.substack.com/p/why-the-abstraction-and-reasoning

[3] https://arcprize.org/competition

[4] https://www.kaggle.com/competitions/arc-prize-2024/

[5] https://arcprize.org/guide

Applications of Genetic Programming

An oft posed question is how much is genetic programming used, "for real"? https://gpbib.cs.ucl.ac.uk/gp-html/jaws30_reply.html Today, although many papers propose new types of GP, most are about applying GP.  Many papers use real world datasets to show how good a novel form of GP is or to compare GP and other AI approaches.   Instead lets concentrate upon papers where GP is just being used and the application itself is the important thing.

Of course most industrialists are not interested in papers.  Indeed they may have sound commercial reasons for not publicising their results or even what they are interested in. Which always means numbers based on published work will be an underestimate.

Nonetheless, taking data for 2023 in the genetic programming bibliography https://gpbib.cs.ucl.ac.uk/ today as typical, about 38% (pm 5%) of papers are on applications.  About a quarter of all GP papers are on: Medicine, Civil Engineering or Material Science, often with an environmental or sustainability emphasis.

Humies 2024, closes Friday 31 May

A quick reminder GP+EM articles published after 2 June 2023 are eligible to enter this year's Human Competitive awards (competition closes to new entries on Friday May 31). Full details on line: https://human-competitive.org/call-for-entries

As with last year, the Humies will be held in hybrid mode, i.e. both in person in Melbourne and online, via video link. Prize money will be sent to the winners via wire transfer.

Entries listed in https://human-competitive.org/awards

The finalists who will battle it out to convince the judges they should be the winner have been announced on  https://human-competitive.org/awards