Top Iwate brewery turns to AI for high-tech assist with sake

The Japan Times

Nanbu Bijin Co. in Ninohe, Iwate Prefecture, is developing an AI tool to find the best time to drain water in the steeping process for rice before it gets steamed. The company aims to see AI put in practical use in several years. "We would like to develop AI to partner with our workers to help resolve the manpower shortage (at breweries in Japan)," said Nanbu Bijin President Kosuke Kuji, 46. The company, whose origins date back to the early 1900s, won the top sake title in the junmai category for its Nanbu Bijin Tokubetsu Junmai at the International Wine Challenge 2017. Junmai sake is made of only rice, kōji (mold) and water.

ScienceAlert Deal: This Service Uses Machine Learning to Find Your Perfect Wine


The world of wine is vast, and it seems like there are more wineries out there than grapes in a vineyard. As such, finding that perfect bottle of vino can feel like a nightmare. And, while asking your friends for recommendations can help refine the process, you can't always rely on their tastes to match your own. So, why not let data do the matching for you? Services like Spotify and Netflix already use artificial intelligence to match their users with music and TV - content that can be just as nuanced as a bottle of Merlot - and they do so with great effect.

Can A.I. usher in a new era of hyper-personalized food?


"My take is that pretty much all the food and beverage products on the market today are awful," Jason Cohen tells me, with fierce conviction. "There are literally no products engineered for me." Cohen is the founder and CEO of Analytic Flavor Systems, an NYC-dobased start-up that aims to usher in a new era of hyper-personalized food. We are meeting at a swank Australian coffee shop near the company's office in the financial district--the kind of place that offers multiple single-origin pour-over options--so he can tell me about his artificial intelligence (A.I.) platform, Gastrograph, which he says can be used to map taste preferences with unprecedented ease and precision. Cohen is lanky and self-possessed, with hair the color of damp straw. He drinks his coffee with the studied concentration of someone who takes flavor extremely seriously. Like many start-up CEOs, Cohen interprets his own dissatisfaction as a sign of a more general problem. It's not just that most grocery store offerings, from snack-cakes and yogurt to green tea and IPA, don't fully thrill our senses. They're also aimed at the lowest common denominator: There's nothing out there truly designed for you. The world of food and beverage manufacturing, Cohen says, is still oriented around "the predominant demographic," the flavors of things tailored to please a coarse approximation of majority appetites.

Big Data vs. Smart Data - DATAVERSITY


Big Data describes massive amounts of data, both unstructured and structured, that is collected by organizations on a daily basis. This Big Data can then be filtered, and turned into Smart Data before being analyzed for insights, in turn, leading to more efficient decision-making. Smart Data can be described as Big Data that has been cleansed, filtered, and prepared for context. There are two primary kinds of Smart Data often discussed by experts in the industry. One form is information picked up by a sensor, and then sent to a nearby collection point, and acted upon, before being sent to an Analytics platform.

27 Incredible Examples Of AI And Machine Learning In Practice


There are so many amazing ways artificial intelligence and machine learning are used behind the scenes to impact our everyday lives and inform business decisions and optimize operations for some of the world's leading companies. Here are 27 amazing practical examples of AI and machine learning. Using natural language processing, machine learning and advanced analytics, Hello Barbie listens and responds to a child. A microphone on Barbie's necklace records what is said and transmits it to the servers at ToyTalk. There, the recording is analyzed to determine the appropriate response from 8,000 lines of dialogue.

Gartner Predicts 3 Ways AI Will Impact Marketing And Improve Customer Experiences


The area that intrigued me the most was in enhancing customer experiences. Mathers elaborates, "We've seen consumer companies like L'Oreal, Whole Foods, and a membership club in the wine and spirits space, innovating how they can simplify, improve and remove barriers to purchase. L'Oreal has built tools into their mobile app so you can apply cosmetics while standing in a drug store and see whether it's the right shade for you. Whole Foods is using some of their tools with their recipes site so you can pop in a couple of ingredients that you have and it starts pushing you a couple more things that you might want to buy in the store. So, growing basket size or helping people expand their grocery list if they're meal planning.

This Brewery Is Using Machine Learning to Create the Ideal IPA


As computers integrated into everyday life, a romanticism emerged: the idea that they might be able to do everything perfectly--from handling your finances to even finding you a mate. And as the field of artificial intelligence continues to grow, a brewery in Virginia has even used this technology to create what it hopes could be the perfect IPA--and the methodology they used is certainly intriguing. Charlottesville's Champion Brewing company recently teamed up with the nearby machine learning company Metis Machine to brew their new ML IPA--a computer's vision of what should essentially be the ideal IPA. And since the project is based in science, Champion was very specific about what data it chose to feed into the computer. "We provided the parameters on which IPAs are judged at the Great American Beer Festival (SRM, ABV, IBU) and matched that range with the 10-best-selling IPAs nationally, as well as the 10 worst selling IPAs at a local retailer and Metis came up with the results," Hunter Smith, owner of Champion Brewing Company said announcing the beer.

Winetitles Media


Advanced machine learning and high-resolution satellite images are set to revolutionise the Australian grape and wine community's regional mapping and vineyard insights. World leading agricultural artificial intelligence software, GAIA (Geospatial Artificial Intelligence for Agriculture), has been developed by Consilium Technology, in partnership with DigitalGlobe and Wine Australia. The software provides groundbreaking insight into the health and quantity of all vineyards across Australia – effortlessly and in real-time. The partnership's initial co-investment will see GAIA deployed in Australia's wine regions to prove that the technology can deliver accurate, timely and cost-effective information about Australia's winegrape vineyards. DigitalGlobe is the world's leading provider of high-resolution Earth imagery.

Irrigation robots could help grow wine grapes in California


We all know by now that robots are the future of farming, and things are no different for winemakers in The Golden State. Faced with the shortage of water and workers, they asked researchers from the University of California to create an irrigation system that needs minimal human input. What the team came up with is a system called Robot-Assisted Precision Irrigation Delivery (RAPID) that uses a machine to monitor and adjust water emitters attached to irrigation lines. The researchers have been working to advance and refine the system since 2016, and RAPID is actually the second version of the project. In a new report, IEEE talks about where the researchers are with it, a bit over a year after it received a $1 million grant from the Department of Agriculture.

Explanations of model predictions with live and breakDown packages Machine Learning

Complex models are commonly used in predictive modeling. In this paper we present R packages that can be used to explain predictions from complex black box models and attribute parts of these predictions to input features. We introduce two new approaches and corresponding packages for such attribution, namely live and breakDown. We also compare their results with existing implementations of state of the art solutions, namely lime that implements Locally Interpretable Model-agnostic Explanations and ShapleyR that implements Shapley values.