Culinary Artificial Intelligence

On Gastronomic Disruption

Algorithmic Modeling Cakes by: Dinara Kasko

In 1997 IBM’s Deep Blue defeated the World Chess Champion, Garry Kasparov. This was not only a defeat against the then Soviet undisputed chess genius but it was a powerful blow to the intellect of the entire human race. This was a pivotal point to both the chess and AI community. Here was a machine that was slaying one of our best and brightest by brute force computational power.

Competitive chess players go through years of grueling training that is mentally taxing. Anyone serious about turning pro in any domain must undergo the same brain rewiring that is extremely time intensive. Gladwell claims it takes at least 10,000 hours of training (that’s 20 hours a week for 10 years) to become successful at something, given you survive all the external and internal hurdles along the way. And even that argument has its critics and outliers.

Observing a chef who takes his career and reputation seriously is like watching a fleet admiral shake down the squadron of his destroyer, except in this case it’s not a flotilla, it’s a kitchen. Some makeshift chefs or pseudo-cooks, rip off best-selling dishes from their competitors — if they think they’re being sly, maybe rip off recipes from another continent. Copy/paste syndrome is easily discoverable now because of the connectivity of social media and creative overlap. In some industries, the ocean is still red, with competitive halibut slithering on the seabed thinking they can operate unnoticed.

A lot of chefs today use different tools to distinguish themselves from the sea of culinary practitioners. Today, style and technology go hand in hand as contemporary chefs step away from classical cooking. Just as cooking styles change and evolve so does the kitchen technology.

Meet Chef Watson!

AI-enabled Chef Watson is a project by IBM and functions as a digital culinary research assistant (sort of like a genie/oracle) with access to a database rich in flavor profiles and recipe ratios — rendering the Flavor Bible obsolete. Chef Watson can help anyone create bizarre and unique dish combinations like a veteran chef with a tech savvy edge. You begin by inputting your desired ingredients into the program, choosing a cooking style and then comb through the algorithm’s output of creative combinations before you pull out your bamboo cutting board. Though not as glamourous as experience gained from rising through the ranks of a Michelin Star restaurant, Watson simulates a chef’s palate and instruction. Machine learning powered cognitive cooking can help chefs step out of their comfort zones and co-create something unusual that titillates the taste buds — given you have the dexterity.

Watson has succeeded in using a quantitative cooking methodology, enabled by analyzing the users’ taste preferences and suggesting psychophysically compatible ingredients. All this jargon may sound complex but on the surface, recipe results are presented on a very user-friendly interface.

Google’s Deep Dream has proved that AI can produce its own art by learning the styles of renaissance artists, and as AI builds more momentum in cuisine, we will quickly branch into different facets of foodtech. So, can machines be more creative than humans? IBM demonstrates how an AI using culinary data just might be.

As Watson’s team point out, even the best chefs build flavour profiles with only two or three ingredients at a time, a time-consuming process — whereas Chef Watson can sift through millions of ingredient combinations and consider countless options simultaneously. As a cognitive system, it learns from human expertise and extends what people can do on their own. Coupled with Bon Appétit’s recipes, Chef Watson reads data from thousands of recipes to understand how different ingredients are used in cuisines and dishes, as well as having an added understanding of food chemistry and the psychology of people’s likes and dislikes. With as little as one user-selected ingredient, Chef Watson can suggest a totally unique flavour profile, measurements, and preparation steps for a dish.

The algorithms created for Chef Watson are fairly generic. In a nutshell, they ingest a corpus of existing creations (recipes from Bon Appetit magazine), implement several scientific theories that help score combination of ingredients (such as the foodpairing method), and then try to combine ingredients in a way that is novel and scores high. There are many other domains that could use this approach, such as perfumery, fashion, interior decorating, product design…

What new developments in foodtech can we expect to see in the next 5 years?

Within 5 years, we’ll see applications that successfully tackle meal planning for the masses. The war has begun, and food geeks can choose between a myriad of companies offering boxed meals, giving meal recommendations, helping you cook with you have on hand, optimizing your dinner choices for your definition of “healthy”, and so on. In the coming years, a handful of winning models and companies will emerge.

What are the most pressing issues in the food supply chain? How can these be solved using technological or scientific breakthroughs?

One major issue is food waste. About 1/3 of the food produced globally is wasted. Part of the problem can be alleviated with technological solutions such as Chef Watson, meal planning, or a kitchen filled with IoT gadgets. But it’s often too convenient to think that issues can simply be solved with technology. There needs to be a change in mentalities as well. Do American restaurants need to serve portions so large that nobody can finish them? Do supermarkets need to sell packages of 8 burger buns when the average US household size (and therefore the number of buns one should need for a single meal) is 2.5? In a world where I can get almost anything delivered to my door the next day (if not the same day), do I really need to stock on food “just in case”?

Legacy Cooks & Multidisciplinary Tinkerers

Imagine trying to source bluefin tuna or Japanese Wagyu without a Google translate search, online payments or a smart phone. I’ve had conversations with anti-technovation restaurateurs and caterers—arms defensively crossed yet strapped with Apple Watches and Fitbits—fear-mongering over their technophobia and dismissive of how blockchain can revolutionize the entire farm-to-table supply chain. In other words, being aware of technology like the IoT can cut cost considerably and help run your new central kitchen more efficiently than your expensive imported Peruvian sous chef, Paolo.

3D printed food has generated on and off hype, mainly by tech-utopians who fantasize about someday printing nostalgic delicacies aboard a Falcon Heavy while fangirling over Musk as they present him a 3D printed Mars Bar in techno-reverence. Until that day comes, a noteworthy marvel that comes to mind is Dinara Kasko’s very impressive 3D printed algorithmic cake model. This geometric statuesque result would have left even Euclid dumbfounded. When patisserie merges with architecture to produce art, the future of food is heading on a multidisciplinary tangent. We could soon see quants and theoretical physicists baking pi pies.

Culinary Easing:

As the world is getting more and more connected it’s become much easier to learn new skills, explore remote fields, find likeminded people (or bots), secure funding or launch a culinary enterprise. Below I’ve included a short list of steps to get you started with planning a restaurant or related business.

1. Elevate your taste: Educate your local and global palate by dining in the good, the bad and the ugly. Seek out diversity and try everything to raise your awareness and refine your taste.

2. Feed your brain: We live in the age of MOOCs where world class education can be accessed online for free. Before relocating to get an expensive certificate, try yourself on a Science & Cooking Harvard X course, guided by top chefs and Harvard researchers from the comfort of your kitchen stool.
Link: [Science & Cooking: Chemistry/Science & Cooking: Physics]

3. Feed your eyes: Seek out the most vibrant and aesthetically plated dishes of the culinary online world. There’s an endless archive of YouTube videos in the world’s best kitchens and Instagram timelines from international chefs, literally trying to feed you.

4. Do the knowledge: Scour the internet for food and beverage reports to learn about the industry and understand market trends. A word to the wise, not all data is created equal. Corporatehold names like the big four and big three usually have recent relevant data, and of course stock up on contacts and insight from F&B trade fairs and festivals.

5. Build a team: Team chemistry is key. It’s important that your team is compatible, understand each other and get along—don’t forget there are knives! StrengthsFinder 2.0 is a great resource for identifying and combining different talents for a better collective yield.

6. Elevate your collective taste: Now with this newfound insight, revisit your favorite restaurants with your comrades. This time analyze and scrutinize what you’re eating and how it’s being served. Discuss, debate, quarrel, get to know each other’s palate.

7. Train and brand: start building a brand online in parallel with your team preparation, this will generate a feverish hype (if done right) in anticipation of your grand opening. Featuring your day-to-day activities makes your image personal, shows brand character and builds a connection with your followers.

8. Soft Launch: host a soft launch or exclusive pop-up dinner to tease the market before opening. Invite strategically for maximum exposure: socialites, hype beasts, foodies and culture influencers.

Innovation favors the bold, those who don’t adeptly adapt, perish. MBA students are drowned in case studies that repeat a time-tested business lesson. Embrace change!

flâneur | seafarer among seafarers | all Medium writing is experimental, opinion or abstract creative expression.