Artificial intelligence information decoder based on bacterial growth patterns

From a box of cookies to The Da Vinci Code, everyone loves to decipher secret messages
.

Depending on the initial conditions used, such as nutrient levels and space constraints, bacteria tend to grow
in a particular way.

The encoding is not one-to-one because the final simulation mode corresponding to each letter is not exactly the same
every time.

You Lingchong, a professor of biomedical engineering at Duke University, explains: "Over a period of time, friends may see a lot of pictures of me, but none of them are exactly the same
.

To encrypt the real information, the encoder ends up creating a series of patterns of movies, each associated with a different letter
.

Try this password yourself
.

_msthash="320080" _msttexthash="22107358">The research was supported
by the National Science Foundation (MCB-1937259), the Office of Naval Research (N00014-20-1-2121), the David and Lucille Packard Foundation, and the Google Cloud Research Credit Program.

Journal Reference:

1. Jia Lu, Ryan Tsoi, Nan Luo, Yuanchi Ha, Shangying Wang, Minjun Kwak, Yasa Baig, Nicole Moiseyev, Shari Tian, Alison Zhang, Neil Zhenqiang Gong, Lingchong You.