View source for 17847068. DATA STORAGE DEVICE WITH NOISE INJECTION simplified abstract (Western Digital Technologies, Inc.)

=DATA STORAGE DEVICE WITH NOISE INJECTION=


==Organization Name==

[[:Category:Western Digital Technologies, Inc.|Western Digital Technologies, Inc.]]


[[Category:Western Digital Technologies, Inc.]]

==Inventor(s)==

[[:Category:Daniel Joseph Linnen of Naperville IL (US)|Daniel Joseph Linnen of Naperville IL (US)]][[Category:Daniel Joseph Linnen of Naperville IL (US)]]

[[:Category:Kirubakaran Periyannan of Saratoga CA (US)|Kirubakaran Periyannan of Saratoga CA (US)]][[Category:Kirubakaran Periyannan of Saratoga CA (US)]]

[[:Category:Ramanathan Muthiah of Bangalore (IN)|Ramanathan Muthiah of Bangalore (IN)]][[Category:Ramanathan Muthiah of Bangalore (IN)]]

==DATA STORAGE DEVICE WITH NOISE INJECTION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17847068 titled 'DATA STORAGE DEVICE WITH NOISE INJECTION

==Simplified Explanation==

The patent application describes procedures for injecting noise into a non-volatile memory (NVM) array. This is done to induce bit flips and information degradation in the data stored in the memory.

* Noise is injected by adjusting read voltages, causing bit flips, while using feedback to control the amount of information degradation.
* Random data is combined with itself iteratively to achieve a target percentage of random 1s or 0s. This random data is then combined with data read from the NVM array.
* Dead pixels in charge coupled devices (CCDs) are emulated by randomly zeroing out pixels.
* Timing, voltage, and current values used in data transfer are adjusted outside their specified margins to induce bit flips and inject noise into the data.

Potential applications of this technology:

* Dataset augmentation: The noise-injected data can be used to expand and diversify training datasets for machine learning models.
* Testing of deep neural networks (DNNs): The noise-injected data can be used to evaluate the robustness and performance of DNNs.

Problems solved by this technology:

* Lack of diverse training data: By injecting noise into the data, the technology helps address the problem of limited and homogeneous training datasets.
* Testing limitations: The technology provides a method to test the performance and resilience of DNNs by injecting controlled noise into the data.

Benefits of this technology:

* Improved machine learning models: Dataset augmentation with noise-injected data can enhance the accuracy and generalization capabilities of machine learning models.
* Robustness testing: The ability to inject controlled noise into data allows for comprehensive testing of DNNs, ensuring their reliability and performance in real-world scenarios.


==Original Abstract Submitted==

Noise injection procedures implemented on the die of a non-volatile memory (NVM) array are disclosed. In one example, noise is injected into data by adjusting read voltages to induce bit flips while using feedback to achieve a target amount of information degradation. In another example, random data is iteratively combined with itself to achieve a target percentage of random 1s or 0s, then the random data is combined with data read from the NVM array. In other examples, pixels are randomly zeroed out to emulate dead charge coupled device (CCD) pixels. In still other examples, the timing, voltage, and/or current values used within circuits while transferring data to/from latches or bitlines are adjusted outside their specified margins to induce bit flips to inject noise into the data. The noise-injected data may be used, for example, for dataset augmentation or for the testing of deep neural networks (DNNs).



[[Category:G06F3/06]]