It’s not literal liquid, of course, it’s an algorithm! MIT researchers have successfully created a neural network that adjusts to changes experienced by real-world systems. This network could improve decision-making in self-driving cars and medical diagnosis. Ramin Hasani, the study paper’s lead author, said that it is a way forward:
Listen beautiful relax classics on our Youtube channel.
Hasani said the system is inspired by a tiny worm — the C. elegans:
It only has 302 neurons in its nervous system yet it can generate unexpectedly complex dynamics.
The code was influenced by the way the C. elegans’ neurons activate and communicate with each other through electrical impulses.
Hasani structed his neural network so that the parameters can change over time based on the results of a nested set of differential equations.
This allows it to continue learning after the training phase, making it more resilient to unexpected situations, like heavy rain covering a camera on a self-driving car.
Image via The Next Web