Keerthan Subraya Shagrithaya

Title: Keerthan Subraya Shagrithaya: Innovator in Neural Network Technologies

Introduction

Keerthan Subraya Shagrithaya is a prominent inventor based in Bengaluru, India. He has made significant contributions to the field of neural networks, focusing on enhancing their efficiency and performance. With a total of 3 patents to his name, his work is paving the way for advancements in artificial intelligence.

Latest Patents

One of his latest patents is titled "Accelerating Neural Networks with One Shot Skip Layer Pruning." This invention involves systems, methods, and devices for pruning a convolutional neural network (CNN). The process includes selecting a subset of layers from the CNN and determining the salience of each filter in those layers. Based on this salience, a subset of filters is pruned, which can include either odd or even numbered layers, depending on the implementation.

Another notable patent is "Efficient Weight Clipping for Neural Networks." This invention discloses systems, apparatuses, and methods for implementing one-sided per-kernel clipping and weight transformation for neural networks. It quantizes various parameters of a neural network from higher-bit to lower-bit representations, thereby reducing memory utilization and power consumption. The technique employs a global strategy for clipping, ensuring that the system retains as much information as possible without sacrificing accuracy during the quantization process.

Career Highlights

Keerthan is currently employed at Advanced Micro Devices Corporation, where he continues to innovate in the field of neural networks. His work is instrumental in developing more efficient algorithms and systems that enhance the capabilities of artificial intelligence technologies.

Collaborations

He collaborates with talented individuals such as Arun C Ramachandran and Chandra Kumar Ramasamy, contributing to a dynamic and innovative work environment.

Conclusion

Keerthan Subraya Shagrithaya is a key figure in the advancement of neural network technologies, with a focus on efficiency and performance. His patents reflect a deep understanding of the complexities involved in artificial intelligence, and his contributions are likely to have a lasting impact on the field.