US Patent Application 17727454. IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS simplified abstract
Contents
IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS
Organization Name
Inventor(s)
Gufeng Zhang of San Jose CA (US)
Milad Olia Hashemi of San Francisco CA (US)
Ashish V. Naik of Los Altos CA (US)
IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 17727454 Titled 'IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS'
Simplified Explanation
This abstract describes a method for predicting the likelihood of a computer memory failure in the future. The method involves obtaining training data inputs that include information about correctable memory errors and whether these errors led to a failure of the computer memory. Image representations of the correctable memory error data are generated and processed using a machine learning model to estimate the likelihood of a future failure. The estimated likelihood is then compared to the actual failure data, and the model parameters are updated based on the difference between the two.
Original Abstract Submitted
Methods, systems and apparatus, including computer programs encoded on computer storage medium, for predicting a likelihood of a future computer memory failure. In one aspect training data inputs are obtained, where each training data input includes correctable memory error data that describes correctable errors that occurred in a computer memory and data indicating whether the correctable errors produced a failure of the computer memory. For each training data input, image representations of the correctable memory error data included in the training data input are generated. The image representations are processed using a machine learning model to output an estimated likelihood of a future failure of the computer memory. A difference between the estimated likelihood of the future failure of the computer memory and the data indicating whether the correctable errors produced a failure of the computer memory is computed. Values of model parameters are updated using the computed difference.
