Want to Invent A New Recipe? IBM Has a Computer For That

The company is developing a cyberchef that will invent new recipes with unique ingredients

  • Share
  • Read Later
Getty Images
Eating food involves more than the five basic taste groups; it is a multisensory experience that also blends chemistry and psychology. For most people, preparing meals off-the-cookbook is an exciting challenge at best and an insurmountable obstacle at worst—but not for much longer, if IBM has any say in the matter. The tech company is developing a cyberchef to assist these these average, non-Iron Chefs, whose cooking sensibilities are limited to “peanut butter + strawberry jelly = good.”
In December, IBM research scientist Dr. Lav Varshney wrote a blog post about the system, describing it as “a learning system that adds one more dimension to cognitive computing: creativity.” His research team is developing a way to analyze foods in terms of chemical compounds and psychophysical data and models on which chemicals produce perceptions of pleasantness, familiarity and enjoyment, for an end result that is a unique recipe, using combinations of ingredients that are scientifically flavorful.

Most importantly, the system will pluck underused ingredients or combinations—venison, bear meat, fenugreek, etc.—and add them to recipes to excite palates. Inductive reasoning will play off of human perception; the system will act as the epicuriously creative neural pathway that you wish you had. This is the same type of thinking that IBM supercomputer and Jeopardy! champ Watson used to outsmart Ken Jennings and Brad Rutter by getting the same answers, just faster and more efficiently.

(MORE: Equality Sans: A Typeface for Marriage Equality)

IBM’s still-unnamed system is more than just a helper for stumped grocery shoppers. The creativity component also has a crucial social component. In addition to pleasing picky eaters and finding ways to substitute healthy ingredients for diet-conscious consumers, it can also help resource-poor areas make the most of their produce.

“Many communities in sub-Saharan Africa only have access to a few base ingredients for any given meal,” Varshney wrote. “But limited resources should not eliminate the enjoyment of food. A creative computer can optimize flavor profiles within these constraints, creating a variety of never thought of meals that please the palate, encourages consumption, and helps prevent malnutrition.”
The culinary system has access to large databases of recipes from online, governmental, and specialized sources. It also takes into account cultural notions of good food, according to Fast Co. Design. It describes the process as such:
From 50 recipes of quiche, the system can infer that a “good” combination of ingredients for any variation of quiche would include eggs, at least one vegetable, and three spices. To generate these food leads, if you will, AI cross references three databases of information:
  1. A recipe index containing tens of thousands of existing dishes that allows the system to infer basics like “what makes a quiche a quiche”

  2. Hedonic psychophysics, which is essentially a quantification of whether people like certain flavor compounds at the molecular level

  3. Chemoinformatics, which sort of marries these two other databases, as it connects molecular flavor compounds to actual foods they’re in

IBM isn’t trying to create a robochef to rule us all. Rather, the system is supposed to a handy companion to curious cooks. To demonstrate this, the Institute of Culinary Education provides professional chefs to test the computed recipes. The result is relatively successful, Varshney told Fast Co.

“Nothing is really crazily bad, though there are certainly things we’ve tried making that weren’t spectacular, like a mideastern mushroom stroganoff,” he said. “Out of the 20 most recent dishes, 17 or 18 have been really good.”