Name: MIT’s new ‘liquid’ AI could help robots adapt to changing conditions
Brand: thenextweb.com
SKU: thenextweb-com-83
Availability: OnlineOnly

critic

MIT’s new ‘liquid’ AI could help robots adapt to changing conditions

preview

Human-centric AI news and analysisMIT researchers have invented an adaptive “liquid” neural network&nbsp;that could improve decision-making in self-driving cars and medical diagnosis.The algorithm adjusts to changes experienced by real-world systems by changing their underlying equations as they receive new data.“This is a way forward for the future of robot control, natural language processing, video processing — any form of time series data processing,” Ramin Hasani, the study paper’s&nbsp;lead author. “The potential is really significant.”[Read: ]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&nbsp;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.The liquid network’s small number of highly expressive neurons also makes it easier to interpret its decisions.“Just [by] changing the representation of a neuron, you can really explore some degrees of complexity you couldn’t explore otherwise,” said Hasani.In tests, the network performed promisingly in predicting future values in datasets, ranging&nbsp;from atmospheric chemistry to traffic patterns.Its small size also significantly reduced the computing costs.Hasani said he now wants to prepare the system for real-world applications:We have a provably more expressive neural network that is inspired by nature. But this is just the beginning of the process. The obvious question is how do you extend this? We think this kind of network could be a key element of future intelligence systems.You can read the study paper on the pre-print server .Published January 29, 2021 — 16:35 UTCRead more

Human-centric AI news and analysisMIT researchers have invented an adaptive “liquid” neural network&nbsp;that could improve decision-making in self-driving cars and medical diagnosis.The algorithm adjusts to changes experienced by real-world systems by changing their underlying equations as they receive new data.“This is a way forward for the future of robot control, natural language processing, video processing — any form of time series data processing,” Ramin Hasani, the study paper’s&nbsp;lead author. “The potential is really significant.”[Read: ]Hasani said the system is inspired by a...

public

Thomas Macaulay

The Next Web (TNW) is a website and annual series of conferences focused on new technology and start-up companies in Europe. The Next Web company was established in 2006 by co-founders Boris Veldhuijzen van Zanten and Patrick de Laive in Amsterdam, Netherlands, and a technology news website of the same name was started in 2009. On 5 March 2019, the Financial Times purchased a majority stake in TNW.

https://en.wikipedia.org/wiki/The_Next_Web

thenextweb.com

Credible

Speculation

Anecdotal Evidence

Generalization

Stacking the Deck

Appeal to Authority

Straw Man

Slippery Slope

Emotional Appeal

Red Herring

False Dilemma

Illogical

Moral Equivalency

Ad Hominem

Correlation w/o Causation

Semantics

Begging the Question

Faulty Analogy

Non Sequitur

Bandwagon

Dogmatism

Failing Occam's Razor

Biased

Pure Opinion

Hit Piece

Racial Bias

National Bias

Religious Bias

Financial Incentive

Political Agenda

Gender Bias

Misused Image/Video

Study Misinterpreted

Mistake

Misused Term

Science Misrepresented

Factual Error

Satire

Surface Level

Lack of Reliable Sources

Sensational

Not Credible

Investigative

Balanced

Well Sourced

Great Context

sports

entertainment

U.S.

international

business

technology

science

culture

politics

media

health

MIT’s new ‘liquid’ AI could help robots adapt to changing conditions

No article scores yet.

CRITIC REVIEWS

PUBLIC REVIEWS