This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
UK firm uses AI to brew ‘self-improving’ beer
A UK firm has launched the ‘world’s first’ beer brewed by artificial intelligence.
IntelligentX has launched a range of four AI beers (Photo: IntelligentX)
London-based IntelligentX uses a complex machine learning algorithm to determine what consumers like about its beers, then brews new versions which are more finely tuned to their tastes.
IntelligentX is partnership between machine learning firm Intelligent Layer, founded by former Oxford University machine-learning PhD Rob McInerney, and 10x, a creative agency founded by former M&C Saatchi director Hew Leith.
After trying one of the beers, consumers give their feedback on its flavours to IntelligentX’s algorithm via a Facebook Messenger bot.
The algorithm, which is called ABI (Automated Brewing Intelligence), uses this customer feedback data to tell IntelligentX’s master brewer what to brew next.
ABI also has a bank of ‘wildcard’ ingredients, such as adding fruit to a recipe, in a bid to create beer that pushes the boundaries of what’s possible within craft brewing.
Using a combination of reinforcement learning and a form of algorithmic decision-making called Bayesian optimisation, ABI is able to learn from experience by being ‘rewarded’ when it does something good.
The algorithm’s ultimate objective is to keep learning and win a major beer competition, the company said.
The AI beers, which are available now, priced at £4.50 each, from ‘open brewery’ UBrew in Bermondsey, have gone through 11 evolutions so far. They come in four styles: Golden AI (derived from a classic british golden ale recipe using Styrian Golding hops); Amber AI (derived from a British bitter); Pale AI (derived from an American pale ale recipe using Cascade hops); and Black AI (derived from a classic porter recipe).
The beer will be also be available to order online at intelligentx.ai “in the coming weeks”, while the company said it was in talks with several Michelin-starred restaurants about stocking the product.
IntelligentX co-founder Hew Leith said that by using artificial intelligence the company was in effect endowing the brewer with “superhuman skills”.
“We believe the future is a place where AI augments humans’ skills,” he said.
“In this case we’re using AI to give our brewer superhuman skills, enabling them to test and receive feedback on our beer more quickly than ever before. This means we can respond to consumers’ changing tastes faster than traditional brewers.”
Rob McInerney, whose PHD thesis was on machine decision-making under uncertainty, likened the AI technology used to brew the IntelligentX beer to that used by Google DeepMind to create AlphaGo, which last year became the first computer program to beat a professional human player of the Chinese strategy board game Go.
“What Google’s Deepmind has achieved with AlphaGo is extremely impressive,” he said. “However, what happens if you don’t have millions of datapoints to train a deep learning algorithm?
“Clearly we can’t make a million beers, so we need to carefully manage uncertainty in the model so that what information we do have is used very efficiently. Instead of deep networks we use a Bayesian non-parametric approach which is better suited to this type of problem.
“We also work very hard to learn as much as possible from the brewer directly, so this really becomes a joint effort between man and machine.”
As well as using consumer feedback to refine its beers, IntelligentX plans to open-source every recipe created by the algorithm, allowing customers to recreate their favourite beers at home.
“Our beer is one of the world’s first uses of AI to improve physical products,” Leith added.
“We think it’s an area that has huge potential. Imagine emotive products like perfume, coffee, or chocolate which are finely tuned to people’s tastes by machine learning algorithms.”