This New ‘Liquid’ Neural Network Learns On The Job

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: 

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 


Newest 2
Newest 2 Comments

Thank you for a really awesome blog. This is a Valuable and excellent post, I am so happy I found this I am hoping for the same best post from you in the future as well. https://buylinkedinaccount.com/
Abusive comment hidden. (Show it anyway.)
Thanks for sharing the post. This is a Valuable and excellent post, as share good stuff with good ideas and concepts. Thanks again. Keep it up.
Abusive comment hidden. (Show it anyway.)
Login to comment.




Email This Post to a Friend
"This New ‘Liquid’ Neural Network Learns On The Job"

Separate multiple emails with a comma. Limit 5.

 

Success! Your email has been sent!

close window
X

This website uses cookies.

This website uses cookies to improve user experience. By using this website you consent to all cookies in accordance with our Privacy Policy.

I agree
 
Learn More