MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202617049028 A) filed by International Business Machines Corporation on April 17, 2026, for Layer Normalization For Calibrated Uncertainty In Deep Learning.
Inventors include Frick, Thomas; Rigotti, Mattia; Antognini, Diego; Giurgiu, Ioana; and Malossi, Adelmo Cristiano Innocenza.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: Layer normalization in machine learning applications that includes sampling a random set of activations corresponding to a fix fraction of the overall activations to provide a plurality of subsampled activations; computing the average across the plurality of subsampled activations; and computing the standard deviation across the plurality of subsampled activations. The layer normalization further includes employing two statistics including the average of the subsampled activations and the standard deviation across the plurality of subsampled activations to normalize all of the activations as a layer normalization.
Disclaimer: Curated by HT Syndication.
