Carnegie Mellon University

Data Storage Systems Center

College of Engineering


DNN-Based Machine Learning Channel for HDD Data Detection

We have been developing machine learning (ML) channels as a possible alternative data detection/recovery technology for hard disk drives (HDD). One of the main objectives of this research project is to obtain in-depth understanding of the ML capability in this particular application as well developing new ML algorithms/schemes to possibly enhance the channel capability. Over the past 12 months, we have developed a deep neural network (DNN) based ML channel for data detection in the presence of both electronic and transition jitter noise. Performance comparable to current state-of-the-art detection channel has been obtained. Currently, the research focuses on developing ML channel for resolving inter-track interference at high track densities.

For Sponsors

Related Publications

"Deep Neural Network: Data Detection Channel for Hard Disk Drives by Learning",  Y Qin, JG Zhu,  IEEE Transactions on Magnetics 56 (2), 1-8 (2020) [Get it]

Related Presentations

Deep Neural Network: Data Detection Channel by Learning. Yuwei Qin. 2019 DSSC Fall Technical Review. [Get it]

Request your Sponsor Account.
Having trouble accessing content? Contact Chloë Mattingly for assistance.