Neha Chopra

Title: Neha Chopra: An Inventor in Deep Learning

Introduction

Neha Chopra is an inventor based in Gurugram, India. Her work includes a patent application concerning deep-learning models and the preservation of relationships between response variables and selected explanatory variables.

Latest Patents

Chopra is associated with 1 patent, titled “Provisioning Deep Learning (DL) Models That Preserve Relationships Between Response Variables and Selected Explanatory Variables.” The disclosed implementations describe training a denoising stacked autoencoder (DAE) with a noisy dataset containing noisy and non-noisy subsets. They also describe using parameters from at least part of the DAE encoder in an artificial neural network with multiple hidden layers, training that network, and providing a version for inference.

Career Highlights

Chopra is associated with Accenture Global Solutions Limited. The patent’s described approach connects denoising autoencoder training with neural-network inference, while aiming to preserve relationships between selected explanatory variables and response variables.

Collaborations

Georgios Passalis and Sneha Chate are identified as Chopra’s coworkers. Their shared association provides context for her professional environment, though the supplied information does not specify their roles in the patent.

Conclusion

Neha Chopra’s listed patent focuses on applying denoising autoencoder training to deep-learning models while preserving relationships among important variables.