Machine Learning In The Kitchen Makes For Tasty Mashup Desserts

What did you do during lockdown? A whole lot of people turned to baking in between trips to the store to search for toilet paper and hand sanitizer. Many of them baked bread for some reason, but like us, [Sarah Robinson] turned to sweeter stuff to get through it.

The first Cakie ever made. Image via Google Cloud

Her pandemic ponderings wandered into the realm of baking existentialist questions, like what separates baked goods from each other, categorically speaking? What is the science behind the crunchiness of cookies, the sponginess of cake, and the fluffiness of bread?

As a developer advocate for Google Cloud, [Sarah] turned to machine learning to figure out why the cookie crumbles. She collected 33 recipes each of cookies, cake, and bread and built a TensorFlow model to analyze them, which resulted in a cookie/cake/bread lineage for each recipe in a set of percentages. Not only was the model able to accurately classify recipes by type, [Sarah] was able to use the model to come up with a 50/50 cookie-cake hybrid recipe. The AI delivered a list of ingredients to which she added vanilla extract and chocolate chips for flavor. From there, she had to wing it and come up with her own baking directions for the Cakie.

Continue reading “Machine Learning In The Kitchen Makes For Tasty Mashup Desserts”

[Ben Krasnow] Did It All For The (Perfect) Cookie

[Ben Krasnow] is on a mission. He’s looking for the perfect chocolate chip cookie. To aid him in this noble endeavor, he’s created the cookie perfection machine. From cleaning with plasma, to a DIY CT scanner, to ruby lasers, to LED contact lenses, [Ben] has to be one of the most prolific and versatile hackers out there today. What better way to relax after a hard day of hacking than to enjoy a glass of milk and a perfect chocolate chip cookie?

This is actually an update to the machine we first saw back in 2012. [Ben] has loaded his machine up with ingredients, and has everything under computer control. The machine will now dispense the exact amount of ingredients specified by the computer, measured by a scale. Everything happens one cookie at a time. The only downside is that the machine doesn’t have a mixer yet. [Ben] has to mix a single cookie’s worth of dough for every data point. His experiments have returned some surprising results. Too little flour actually results in a crisper cookie, as the wetter dough spreads out to a thinner layer. [Ben] also found that adding extra brown sugar also doesn’t result in a more chewy cookie. Even though he’s still in the early experimentation phases, [Ben] mentions that since it’s hard to make a bad chocolate cookie, even his failures taste pretty good.

Continue reading “[Ben Krasnow] Did It All For The (Perfect) Cookie”