AlphaGo Zero: the smartest self-taught AI

AlphaGo Zero: the smartest self-taught AI

AI is often reliant on largescale datasets supplied by humans to learn an algorithm. AlphaGo Zero, however, has successfully taught itself.

Google’s latest artificial intelligence, AutoML, can now code itself better than its human counterparts can, after teaching itself basic programming. Google’s other recent and successful AI had been AlphaGo. A year ago, AlphaGo beat the world’s best Go player, but this AI has now been beaten every single time by its newest update, the AlphaGo Zero.


“We’ve actually removed the constraints of human knowledge”


This development changes the game for artificial intelligence because in a self-teaching dynamic there is no chance for human error transferring to the AI. A flawed human input data set can lead to flawed AI algorithms, but when the AI entirely develops the algorithm itself – there’s no room for mistakes.

AlphaGo Zero blows its predecessor out of the water

Just over a year ago, AlphaGo AI beat the Korean Go 18-time world champion for the first time, surprising the world with its ability. Now, AlphaGo Zero has blown its predecessor out of the water.

The ancient board game Go may seem like a trivial task for an AI to learn, but it’s possible 10,170 moves means there is a lot of complicated information in playing the game and building an algorithm to do so perfectly. It is for this reason the AlphaGo Zero has the potential to work with other data, such as particle physics, quantum chemistry, or drug discovery.

AlphaGo Zero is also more efficient; the previous AlphaGo used 48 TPUs (AI processors built by Google) whereas this new version uses only four. Deepmind co-founder Demis Hassabis has explained that AlphaGo can be thought of as a very good machine for searching through complicated data, but AlphaGo Zero has the possibility of being reprogrammed for far more potential.

How does AlphaGo Zero work?

AlphaGo Zero becomes its own teacher. It does this by a form of reinforcement learning, starting of with a blank neural network. It plays the game of Go against itself, combining this neural network with a search algorithm. The neural network then learns to predict moves.

This updated neural network recombines itself with the search algorithm. The process repeats as AlphaGo Zero learns more with each game that it plays. The quality of the self-play games improves: from constant practice, AlphaGo Zero’s neural network becomes more and more refined, increasing its knowledge by learning from itself. As AlphaGo Zero is the strongest Go player in the world, there’s no one better to learn from.

Earlier versions of AlphaGo used a “policy network” to select the next move to play, whilst a “value network” predicted the winner. There is just one neural network in AlphaGo Zero, meaning that it can train itself more efficiently.

Image from http://deepmind.com/

Bekki Barnes

With 5 years’ experience in marketing, Bekki has knowledge in both B2B and B2C marketing. Bekki has worked with a wide range of brands, including local and national organisations.

How E-commerce Marketers Can Win Black Friday

Sue Azari • 11th November 2024

As new global eCommerce players expand their influence across both European and US markets, traditional brands are navigating a rapidly shifting landscape. These fast-growing Asian platforms have gained traction by offering ultra-low prices, rapid product turnarounds, heavy investment in paid user acquisition, and leveraging viral social media trends to create demand almost in real-time. This...

Why microgrids are big news

Craig Tropea • 31st October 2024

As the world continues its march towards a greener future, businesses, communities, and individuals alike are all increasingly turning towards renewable energy sources to power their operations. What is most interesting, though, is how many of them are taking the pro-active position of researching, selecting, and implementing their preferred solutions without the assistance of traditional...

Is automation the silver bullet for customer retention?

Carter Busse • 22nd October 2024

CX innovation has accelerated rapidly since 2020, as business and consumer expectations evolved dramatically during the Covid-19 pandemic. Now, finding the best way to engage and respond to customers has become a top business priority and a key business challenge. Not only do customers expect the highest standard, but companies are prioritising superb CX to...

Automated Testing Tools and Their Impact on Software Quality

Natalia Yanchii • 09th October 2024

Test automation refers to using specialized software tools and frameworks to automate the execution of test cases, thereby reducing the time and effort required for manual testing. This approach ensures that automation tests run quickly and consistently, allowing development teams to identify and resolve defects more effectively. Test automation provides greater accuracy by eliminating human...

Custom Software Development

Natalia Yanchii • 04th October 2024

There is a wide performance gap between industry-leading companies and other market players. What helps these top businesses outperform their competitors? McKinsey & Company researchers are confident that these are digital technologies and custom software solutions. Nearly 70% of the top performers develop their proprietary products to differentiate themselves from competitors and drive growth. As...

The Impact of Test Automation on Software Quality

Natalia Yanchii • 04th October 2024

Software systems have become highly complex now, with multiple interconnected components, diverse user interfaces, and business logic. To ensure quality, QA engineers thoroughly test these systems through either automated or manual testing. At Testlum, we met many software development teams who were pressured to deliver new features and updates at a faster pace. The manual...