<div dir="ltr">"Whereas most machine learning algorithms can’t hone their skills
beyond an initial training period, the researchers say the new approach,
<a href="https://news.mit.edu/2021/machine-learning-adapts-0128">called a liquid neural network</a>,
has a kind of built-in “neuroplasticity.” That is, as it goes about its
work—say, in the future, maybe driving a car or directing a robot—it
can learn from experience and adjust its connections on the fly.
<p>In a world that’s noisy and chaotic, such adaptability is essential."</p><p><a href="https://singularityhub.com/2021/01/31/new-liquid-ai-learns-as-it-experiences-the-world-in-real-time/">https://singularityhub.com/2021/01/31/new-liquid-ai-learns-as-it-experiences-the-world-in-real-time/</a> <br></p><p><br></p>
</div>