Company Filing History:
Years Active: 2016-2023
Title: Keshava Prasad: Innovator in Neural Network Processing
Introduction
Keshava Prasad is a notable inventor based in Suwon-si, South Korea. He has made significant contributions to the field of neural network processing, holding three patents that showcase his innovative approach to technology.
Latest Patents
One of his latest patents is a "Device and method for processing convolution operation using kernel." This invention provides a method and apparatus for processing a convolution operation in a neural network. The apparatus includes a memory and a processor configured to read one of the divided blocks of input data stored in memory. It generates an output block by performing the convolution operation on the divided block with a kernel, creates a feature map using the output block, and writes the feature map to memory.
Another significant patent is the "Method and apparatus for shuffling data using hierarchical shuffle units." This invention outlines a method and corresponding apparatus for processing a shuffle instruction. The shuffle units are arranged in a hierarchical structure, where each unit generates a shuffled data element array by performing shuffling on an input data element array. The hierarchical structure includes an upper shuffle unit and a lower shuffle unit, with the shuffled data element array output from the lower unit being input to the upper unit as part of the input data element array.
Career Highlights
Keshava Prasad has worked with prominent companies, including Samsung Electronics Co., Ltd. and Samsung Electronics Co., Ltd. His experience in these organizations has allowed him to develop and refine his innovative ideas in technology.
Collaborations
He has collaborated with notable coworkers such as Yeon Bok Lee and Young Hwan Park, contributing to various projects and advancements in their field.
Conclusion
Keshava Prasad's work in neural network processing and data shuffling has positioned him as a key innovator in technology. His patents reflect his commitment to advancing the capabilities of neural networks and data processing methods.