We use cookies to provide you with a better experience. If you continue to use this site, we'll assume you're happy with this. Alternatively, click here to find out how to manage these cookies

hide cookie message

Computer Learns Board Games From Two-Minute Clips, Beats Humans Right After

A computer scientist has come up with an a learning algorithm that will let computers beat us at our own board games.

As of right now, we're officially one step closer to Skynet. Like the computer antagonist, computer scientist Lukasz Kaiser's machine learning software (PDF) is capable of learning at accelerated speeds. Unlike everyone's favorite Cyberdine Systems mistake, this one doesn't need military-grade hardware--it just needs a laptop with a 4GB RAM, a 2.13GHz Intel L9600 processor, and only one processor core.

In his recently published paper, Kaiser outlined how a system guided by a decision-making engine of sorts can learn how to play competently games with only a minimal amount of background data.

This is where things get a little technical, so bear with us: Kaiser states that while computer scientists have done a great amount of work in regards to computerized object recognition and visual scene interpretations, "only a few systems with the capacity for learning higher-level concepts has been presented thus far." According to Kaiser, our computers are pretty good at deriving sequences of higher-level symbolic data from video streams, but we still have a long way to go when it comes to learning from it.

He argues that a more nuanced approach using relational structures and multiple logic systems is better suited for learning from visual data in comparison to the standard practice of utilizing formulas and singular logic systems. "These two fundamental changes allow us to demonstrate a system that--knowing only about rows, columns, diagonals and differentiating pieces--learns games like Connect Four, Gomoku, Pawns or Breakthrough, each one from a few intuitive video demonstrations, together around 2 minutes in length."

Is this where we start preparing for the rise of the machines? Not quite yet. Kaiser still needs to figure out how to get the system to solve problems requiring "hierarchical, structured learning or a form of probabilistic formulas." Until then, we're safe. After that, it's anyone's game.

[Aukasz Kaiser (PDF) via Gizmodo]

Cassandra Khaw is an entry-level audiophile, a street dancer, a person who writes about video games for a living, and someone who spends too much time on Twitter.

Like this? You might also enjoy...

Get more GeekTech: Twitter - Facebook - RSS | Tip us off

IDG UK Sites

Best Christmas 2014 UK tech deals, Boxing Day 2014 UK tech deals & January sales 2015 UK tech...

IDG UK Sites

Apple's 2014 highlights: the most significant Apple news of 2014

IDG UK Sites

2015 creative trends: 20 leading designers & artists reveal the biggest influences & changes coming)......

IDG UK Sites

Ultimate iOS 8 Tips: 35 awesome and advanced tips for using iOS 8 on iPhone and iPad