MIT’s New ‘Liquid’ Neural Network Learns From Experience So Robots Can Adapt to Changes

MIT liquid neural network
MIT researchers have developed a neural “liquid” network that varies its equations’ parameters, enhancing its ability to analyze time series data. (Image credit: Jose-Luis Olivares, MIT)
Most machine learning algorithms can’t learn from experiences beyond initial training. Now, MIT researchers have developed a type of neural network that learns on the job, not just during its […]
To access this page, watch the live streams and videos on-demand, please register free of charge to the WT | Wearable Technologies COMMUNITY.
Previous articleHuami Amazfit GTR 2 LTE And Amazfit T-Rex Pro to Arrive This Year
Next articleWearable Medical Devices Market Expected to Experience Huge Growth by 2030, Says Market Industry Reports
Cathy Russey () is Online Editor at WT | Wearable Technologies and specialized in writing about the latest medical wearables and enabling technologies on the market. Cathy can be contacted at info(at)wearable-technologies.com.