Machine learning students say cheers with AI beers
One of the world鈥檚 oldest industries now has a high-tech twist, with a new South Australian craft beer designed entirely by artificial intelligence, thanks to a special project from the Australian Institute for Machine Learning (AIML) working in partnership with Barossa Valley Brewing.
As part of their machine learning internship, two 成人大片 computer science students, Christopher Fusco and Jash Vira, created a neural network that was able to learn how to make beer by studying a vast trove of brewing records. The result is a unique AI-designed IPA which will be available for sale from early next year.
The Rodney AI虏PA is named in honour of Rodney Brooks, an Australian robotics pioneer and co-founder of iRobot, the company behind the Roomba robot vacuum cleaner.
The can design for The Rodney AI虏PA beer by Barossa Valley Brewing. The beer will be available for limited retail sale from mid-January 2022.
Working under the guidance of AIML鈥檚 machine learning researchers and Barossa Valley Brewing鈥檚 experts, the two students set about building a large dataset from more than 260,000 existing craft beer recipes available online, before creating a neural network that learned how to make beer by studying the data.
鈥淲e generated 200,000 new recipes, and then we trained a neural network to pick the best ones and rank them,鈥 Christopher said.
Most beer contains only four main ingredients: malt, hops, water and yeast. Slight variations in those ingredients鈥攁nd precise changes to the times and temperatures at certain steps of the brewing process鈥攔esult in the diverse variety of beer available today.
But if creating AI that can make its own beer isn鈥檛 complex enough, creating AI that can actually make good beer is significantly more challenging.
鈥淭hat was actually very difficult. We had to come up with our own mathematical formula using statistics from those original recipes,鈥 Christopher said.
鈥淏y getting statistics on these variables, we were able to judge the significance of each variable, this also helped us deal with any possible biases that could have occurred in the data,鈥 Jash added.
成人大片 computer science students Jash Vira (left) and Christopher Fusco (centre) with Barossa Valley Brewing's founder Denham D鈥橲ilva (right).
Data such as how many times particular beer recipes had been viewed online, and how many people said they鈥檇 made it, all give an indication as to a beer鈥檚 popularity. The students then created a neural network that learned to judge the AI鈥檚 own recipes and give each a popularity rating.
AIML鈥檚 neural network produced recipes with around 60 data points, or 鈥榝eatures鈥, that included not just the required ingredients and quantities, but also specific process information such as how to handle the hops, the yeast fermentation temperature, and boil times; as well as predictive indicators for bitterness (IBU), colour (SRM) and alcohol content (ABV).
The project was not without its technical challenges, with the neural network sometimes outputting strange feature outliers, such as absurdly large or small quantities, or very high temperatures.
鈥淲e used some statistical and graphical methods to analyse our data and then decided to cap some of these outliers. This method helped us preserve the inherent variability of the data as well as evaluate if the decision we made appropriately reflected the final product we wanted to create,鈥 Jash said.
The result was 30 potential AI beer candidates. AIML left the final decision on which to brew to the experts at Barossa Valley Brewing.
The brewery鈥檚 founder, Denham D鈥橲ilva, was excited about the opportunity for AI to augment his company鈥檚 creative process, but initially thought the technology was too nascent to add value.
鈥淭he willingness to experiment and create interesting and premium beers has been a foundation of the brewery for 16 years. So, to largely place this process in the hands of AI, was in a word, terrifying,鈥 he said.
鈥淏eer is traditionally a very hands-on process, and even more so for a small craft brewery like Barossa Valley. When you鈥檙e a smaller craft brewery you can鈥檛 compete on scale, so you have to be different and clever.鈥
Australia鈥檚 demand for craft beer is strong. While per-capita consumption of beer, generally, has declined in recent decades, craft beer sales are growing at a rate of 10% per year.
鈥淢ost people think of AI and machine learning as something that only the huge tech companies can do. This project has shown us that AI can take our artisanal skills and augment them to allow us to compete.鈥 Denham said.
鈥淚t鈥檚 really important that small and medium enterprises embrace the opportunities that AI offers. Craft producers need to get involved to ensure AI incorporates the art which makes us special.鈥
AIML machine learning engineer Lachlan Mares built a portable automatic 'bartender' using a robotic arm. Infrared proximity sensors built into the bar top sense an empty glass and the robot effector dispenses the AI-beer from a standard keg using a solenoid valve.
Christopher and Jash plan to continue on their machine learning career paths, with both students intending to pursue postgraduate studies after completing their undergraduate programs at the end of 2022.
鈥淚 think it鈥檚 a very exciting time for machine learning, because we鈥檙e reaching a stage where we can collaborate with other industries using what we know and what we鈥檙e good at. There鈥檚 a lot of growth in the field,鈥 Christopher said.
To complement the high-tech beer experience, AIML engineers have also built a robotic 鈥榖artender鈥 that can automatically detect when an empty glass is placed on the bar, and quickly refill it with cold beer straight from the keg.
As for the important question of what the AI beer actually tastes like, Denham D鈥橲ilva is enthusiastic.
鈥淚t tastes like the future! Seriously, it鈥檚 a fruit driven IPA which I am very proud of and can鈥檛 wait to release,鈥 he said.
The Rodney AI虏PA by Barossa Valley Brewing will be available for limited retail sale from mid-January 2022.