Post
Algorithmic Cookery & Happy Thanksgiving
Nov 22 2017 · by Friederike
As you are preparing for your Thanksgiving meal, just know that a robotic arm is holding the spoon at the Institute for Culinary Education (ICE); progress is relentless. “The Chef Watson cookbook is a revolutionary display of the creative collaboration of man and machine.” Cognitive Cooking with Chef Watson, culinary and cognitive creativity at your fingertips. Perhaps you should try the Acorn Squash Meat Roast … with English Breakfast Tea.
Jeopardy! It is so 2011. In 2017, there is (of course) a neural network trained to generate recipes developed by Janelle Shane. Try the Pears Or To Garnestmeam or the Shanked Whipping Peanuts:
Image Credit: The Daily Dot
For the literary-minded, Janelle recommends training the neural network first on the works of your favorite author before feeding it recipes. Here is what happens when you use the works of H. P. Lovecraft:
Bake at 350 degrees for 30 to 32 minutes. Test corners to see if done, as center will seem like the next horror of Second House.
Whip ½ pint of heavy cream. Add 4 Tbsp. brandy or rum to possibly open things that will never be wholly reported.
The algorithm adds a helpful note:
NOTE: As this is a tart rather than a cheesecake, you should be disturbed.
Indeed.
Eager to cook your own recipes with char-RNNs (i.e., multilayer recurrent neural networks with a character-level language models)? The code is available here. Do androids dream of cooking electric pies?
If you’ve done your shopping already, take a quick picture of your haul and let the algorithm im2recipe serve you cooking instructions. The algorithm developers collected 1m cooking recipes and 800k food images, the largest publicly available collection of recipe data, and trained a neural network to find a joint embedding of recipes and images, a multi-modal embedding that puts words and images in the same multidimensional embedding space. This embedding allows to retrieve a recipe given an image and an image given a recipe. More importantly, it allows arithmetic with chicken pizza:
v(chicken_pizza) - v(pizza) + v(lasagna) = v(chicken_lasagna)
You can now compute your next meal (Image Credit: MIT).
In 2017, “we can embed that” truly is the new “we can pickle that.” (Pro-tip: challenge it with your left-overs.)
In the days after Thanksgiving, perhaps try the algorithm for personalized diet meal planning or AVA, your intelligent nutrition bot focused on your happiness.
(You’re welcome!)
Finally, you will be pleased to know that the Association for Computing Machinery (ACM) holds a yearly workshop with the appetizing title Multimedia for Cooking and Eating Activities. We have high hopes for Thanksgiving 2018!
We, the entire team at Cloudera Fast Forward Labs, wish you a Happy Thanksgiving.
Cover image credit: Photo by Besjunior/Shutterstock
More from the Blog
-
Older ↓
Post
Nov 2 2017
Interpretability Sci-Fi: The Definition of Success
by — We believe in fiction as an important tool for imagining future relationships to technology. In our reports on new technologies we feature short science fiction stories that imagine the possible implications. The following story, influenced by a certain classic Sci-Fi film, appeared in our Interpretability report. For more on interpretability read a video conversation on interpretability, a gui...
…read more
by Grant
-
Newer ↓
Newsletter
Nov 30 2017
The promise of Automated Machine Learning (AutoML)
Earlier this month The New York Times published an article on Building A.I. That Can Build A.I.. There is a lot of excitement about AutoML due to the scarcity of machine learning (ML) talent: By some estimates, only 10,000 people worldwide have the education, experience and talent needed to build the complex and sometimes mysterious mathematical algorithms that will drive this new breed of ...
…read more
-
Newest ↓
newsletter
Jan 29 2019
Making an interactive UMAP visualization of the MNIST data set
by — UMAP explorer: an interactive visualization of the MNIST data set We’re in the middle of work on our next report, Learning with Limited Labeled Data, and the accompanying prototype. For the prototype’s front-end we wanted to be able visualize and explore the embedding of a large image data set. Once you get into the tens of thousands of points, this can be a challenge to do in the browser. T...
…read more
by Grant