Abhinav Shrivastava

Title: Abhinav Shrivastava: Innovator in Machine Learning and Data Compression

Introduction

Abhinav Shrivastava is a prominent inventor based in Mountain View, CA, known for his significant contributions to the field of machine learning and data compression. With a total of six patents to his name, he has made remarkable strides in enhancing the efficiency and effectiveness of neural networks.

Latest Patents

One of his latest patents is titled "Compression of machine-learned models via entropy penalized weight reparameterization." This patent focuses on systems and methods that learn a compressed representation of a machine-learned model, such as a neural network, by representing the model parameters within a reparameterization space during training. The approach employs a latent-variable data compression method, allowing for a joint maximization of accuracy and model compressibility. Another notable patent is "Learning compressible features," which describes methods and systems for generating features from a dataset using a neural network. This innovation ensures that the first set of features is compressible into a smaller second set while maintaining the same measure of informativeness.

Career Highlights

Abhinav Shrivastava currently works at Google Inc., where he continues to push the boundaries of technology and innovation. His work has been instrumental in developing advanced machine learning techniques that are applicable across various industries.

Collaborations

He collaborates with talented individuals such as Saurabh Singh and Johannes Balle, contributing to a dynamic and innovative work environment.

Conclusion

Abhinav Shrivastava's contributions to machine learning and data compression exemplify the impact of innovative thinking in technology. His patents reflect a commitment to advancing the field and improving the capabilities of neural networks.