'Liquid' machine-learning system adapts to changing conditions

 By techxplore - 2021-01-28

Description

MIT researchers have developed a type of neural network that learns on the job, not just during its training phase. These flexible algorithms, dubbed "liquid" networks, change their underlying equatio ...

Summary

  • MIT researchers have developed a type of neural network that learns on the job, not just during its training phase.
  • Thanks to Hasani's small number of highly expressive neurons, it's easier to peer into the "black box" of the network's decision making and diagnose why the network made a certain characterization. "
  • We think this kind of network could be a key element of future intelligence systems."
  • E-mail the story 'Liquid' machine-learning system adapts to changing conditions Note Your email address is used only to let the recipient know who sent the email.

 

Topics

  1. Machine_Learning (0.47)
  2. Backend (0.2)
  3. Database (0.12)

Similar Articles

New deep learning models: Fewer neurons, more intelligence

By techxplore - 2020-10-14

Artificial intelligence has arrived in our everyday lives—from search engines to self-driving cars. This has to do with the enormous computing power that has become available in recent years. But new ...

10 Deep Learning Terms Explained in Simple English

By datasciencecentral - 2020-12-27

  Deep Learning is a new area of Machine Learning research that has been gaining significant media interest owing to the role it is playing in artificial intel…

Creating synthetic time series data

By Medium - 2021-02-22

We synthetic versions of a time-series dataset, visualize and analyze the results, and discuss several use cases for synthetic time series data.