Subscribe now

Technology

Cooking Watson-style: Supercomputer turns to recipes

Not content with winning quiz shows, IBM's Watson supercomputer is now injecting a little creativity into your kitchen

By Niall Firth

7 January 2015

New Scientist Default Image

An unexpected taste sensation

(Image: Alex Majoli/Magnum Photos)

I LIKE to think I’m a pretty good cook. I’m adventurous, have a decent understanding of the techniques required and I haven’t poisoned anyone – yet. But I still find myself cooking the same tried-and-trusted favourites, using the same old ingredients.

To shake things up, I ask to test the prototype of a cooking app that uses the brain of IBM’s Watson supercomputer to invent new dishes.

The key to the ChefWatson app is the supercomputer’s ability to devour large amounts of information and make links between chunks of it. It has already proved its mettle by winning the quiz show Jeopardy! and is being used to help doctors make cancer diagnoses at Memorial Sloan Kettering Hospital in New York. Now it is attempting to do something computers usually find difficult: using creativity to invent recipes people will actually want to eat.

To provide the data, IBM teamed up with US recipe website Bon Appetit. This has a database of more than 9000 recipes, tagged according to their ingredients, type of dish and cooking style – Cajun or Thai, for example. Watson creates a statistical correlation between ingredients, styles and recipe steps in the database and uses this to work out which ingredients usually go together and what each type of food requires. “That’s how it knows that a burrito, a burger and a soup all need different elements,” says IBM’s Steve Abrams. “It knows a burrito always needs a wrapper of some sort, whereas soup always needs liquid. That’s how you don’t get a runny burrito.”

To use the app, the cook first types in an ingredient they want to use. Next, they decide the amount of experimentation they want Watson to take, ranging from “Keep it classic” to “Surprise me”. Watson then offers the cook further ingredients, styles and dishes that it thinks usually go well with the initial ingredient. They can promote or exclude ingredients by clicking the “Love it” or “Hate it” buttons. Finally, the cook hits search, and Watson analyses its database to come up with a range of basic recipes that can then be further tweaked to make them more or less experimental.

If the cook wants to ramp it up, a database of flavour compounds found in a wide range of foods is also consulted and used to combine ingredients that should theoretically fit together, such as vodka and Brussels sprouts, or cauliflower and chrysanthemum. Psychological research into what flavours people find more or less pleasant is taken into account (PLoS Computational Biology, doi.org/fsw6fd), as is a “surprise” score for combinations of ingredients: the higher the score the less often they are found in recipes together.

“As you move to the experimental end of the scale, you’re looking less at what ingredients go nicely together and more at the flavour compounds that the ingredients have in common,” says Abrams. “It works out what things might go together that you’d never think of.”

Well, that’s the theory at least. From my culinary forays, it’s easy to see why the app is not yet deemed ready for launch. In a creamy pasta dish (I had opted for the “elegant” style), crème fraiche had been replaced by a glass of milk. Another time, with a high experimental setting, Watson told me my tuna bake needed half a kilo of goose meat. I declined.

It was occasionally inspired. As I ramped up the surprise element, Watson suggested I replace clam juice in a classic gumbo dish with the Japanese soup base dashi. It worked – giving the dish a deep savoury flavour that I would never have thought to try out.

Michael Laiskonis, creative director of the Institute of Culinary Education in New York, was one of the first professional chefs to help guide Watson. “It lets you organise creativity in a more structured way, rather than just going in the kitchen and experimenting,” he says.

The plan is for ChefWatson to become more sophisticated and to suck in data from more sources, says Florien Pinel, the project’s lead software engineer. It already scours Wikipedia’s world cuisine pages and looks up nutrition facts in a US Department of Agriculture database for help on determining ingredient proportions.

Apart from the occasional odd ingredient combination, there are a few other bugs in the way ChefWatson conjures creative recipes out of pure data. One tester, Matt McSherry, says it seems to struggle with portion size. Another found that a recipe called for precisely 554 juniper berries, and she was also told to “skin and bone” her tofu.

Overall, McSherry is loving the experience. “I get to muck about in the kitchen with a thinking, reasoning supercomputer. That’s pretty exciting right there,” he says. “It’s the future we were promised as children.”

To try ChefWatson, go to bit.ly/watsoncook

Thai turkey strudel – à la ChefWatson

Serves 6

INGREDIENTS

  • 450g turkey
  • Frozen pastry
  • Half a seeded, minced Thai chili
  • 1¼ tsp rice flour
  • Dash lemongrass
  • Green curry paste
  • 1¾ head lettuce
  • 500g potato, chopped
  • 13 spring onions, chopped
  • 1½ tsp vegetable oil
  • Olive oil spray
  • 115g Gruyère, diced
  • 100g provolone cheese

SUGGESTED STEPS

  • 1. Cook lettuce in boiling water
  • 2. Drain and squeeze dry
  • 3. Heat vegetable oil
  • 4. Add spring onions and Thai chili and sauté for about 7 minutes
  • 5. Finely chop turkey, cheeses, lemongrass and rice flour
  • 6. Transfer to bowl and stir in spring onions, lettuce and potato
  • 7. Season with salt and pepper
  • 8. Preheat oven to 180 °C
  • 9. Spray large baking sheet with oil
  • 10. Stack pastry in layers and spray with olive oil
  • 11. Spread turkey mixture down centre of pastry
  • 12. Fold short sides of pastry over filling, then roll up into log
  • 13. Bake for about 40 minutes
  • 14. Spoon green curry paste on the side and serve

Topics:

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox! We'll also keep you up to date with New Scientist events and special offers.

Sign up