Company Filing History:
Years Active: 2019-2024
Title: Suraj Sudhir: Innovator in Neural Processing Technologies
Introduction
Suraj Sudhir is a prominent inventor based in Santa Clara, CA, known for his contributions to neural processing technologies. With a total of 3 patents, he has made significant strides in the field of computer-implemented methods that enhance the efficiency of neural processing systems.
Latest Patents
One of his latest patents is a "Neural Processing System," which describes a method performed in a neural processing system that includes control processor circuitry and arithmetic logic circuitry. This method involves performing a convolution between an input feature map (IFM) and convolutional filter data, resulting in an output feature map (OFM). The process includes obtaining dimensional characteristic parameters and positional characteristic parameters to effectively generate output work batch data arrays.
Another notable patent is the "Neural Processing Filter." This invention outlines a method for providing a filter in a neural processing unit. It involves receiving input corresponding to target dimensions of the filter and defining the filter as a combination of multiple sub-filters, ensuring that the dimensions equate to the target dimensions while maintaining unequal sub-filter dimensions.
Career Highlights
Suraj has worked with notable companies such as Arm Limited and Oracle International Corporation. His experience in these organizations has contributed to his expertise in developing advanced neural processing technologies.
Collaborations
Some of his coworkers include Yuan C Chou and Jayavarapu Srinivasa Rao, who have collaborated with him on various projects in the field of neural processing.
Conclusion
Suraj Sudhir's innovative work in neural processing systems and filters showcases his commitment to advancing technology in this critical area. His patents reflect a deep understanding of the complexities involved in neural processing, making him a valuable contributor to the field.