Ai Dreams Forum

Artificial Intelligence => AI News => Topic started by: infurl on February 14, 2020, 03:01:41 AM

Title: Abstraction and Reasoning Challenge
Post by: infurl on February 14, 2020, 03:01:41 AM (

In this competition, you’ll create an AI that can solve reasoning tasks it has never seen before. Each ARC task contains 3-5 pairs of train inputs and outputs, and a test input for which you need to predict the corresponding output with the pattern learned from the train examples.

There's a total prize pool of $20k available in this competition. You will need programming skills to enter. You will probably also need to lease some expensive hardware in the cloud to work on it, although I think kaggle may offer access for free. Does anyone have experience with kaggle? (
Title: Re: Abstraction and Reasoning Challenge
Post by: infurl on February 14, 2020, 03:05:04 AM
You can find hints and tips for getting started in the comments on the challenge page.

There is also a Twitter thread about it. (
Title: Re: Abstraction and Reasoning Challenge
Post by: infurl on February 19, 2020, 10:13:54 PM (

This article provides some more background for the Abstract Reasoning Challenge. It goes into some detail about why this challenge is so important.

The Abstract Reasoning Corpus is a set of problem-solving tasks that require general problem-solving skills. There are a few things about ARC that make it especially interesting. First, there aren’t a ton of training examples. The system that wants to solve a set of problems has to learn the rules from a few examples
Another important aspect of ARC is that it levels the ground between AI and humans. The current artificial intelligence landscape is composed of many challenging fields such as computer vision and natural language processing.

Comparing AI performance to humans in those fields is very difficult because we humans have a lot of prior knowledge about the world and can easily take on new challenges. There still isn’t an AI system that incorporates that kind of knowledge. Therefore, any challenge that surrounding image classification and natural language would put AI algorithms at a disadvantage.

But ARC is based on simple visual elements that are easy to parse and require no prior. They strip the advantage that humans have and make it fairer for AI systems to compete. Humans can easily solve most of the problems proposed in ARC not because of their vast knowledge of the world, but thanks to their abstraction and reasoning capabilities.
Despite the enormity (and impossibility) of the task, at the time of this writing, more than 190 teams have applied for the ARC challenge and will be testing their skills. It will be interesting how the competition develops. And perhaps more importantly, it will be exciting to see what new discoveries we make in the interim.