Paper
German Scientists Predict Chaotic Signals Using 400 Droplet Particles, Achieving About 1/10 the Accuracy of Memristor-Based Solutions
A team from the University of Konstanz and the University of Stuttgart in Germany used 400 silica microparticles (radius 3 μm) suspended in liquid to form a reservoir, successfully predicting the chaotic Mackey-Glass sequence and achieving an F1 score of 0.90 in anomaly detection tasks. The system's single-step prediction normalized root mean square error is about 0.1, roughly one-tenth the accuracy of memristor-based solutions (error 0.01 or lower). The results have been published in the journal Communications, Artificial Intelligence, and Computing.
Read the original (opens in a new tab)
News stream data aggregated by AI HOT