Tejaswini Pedapati

Title: Tejaswini Pedapati: Innovator in Neural Networks

Introduction

Tejaswini Pedapati is a notable inventor based in New York, NY (US). She has made significant contributions to the field of neural networks, holding a total of 4 patents. Her work focuses on enhancing machine learning systems through innovative methodologies.

Latest Patents

One of her latest patents is titled "Neural capacitance: neural network selection via edge dynamics." This invention involves removing an output layer from a pre-trained neural network model and incorporating a neural capacitance probe unit with multiple layers. The probe unit is initialized randomly, and the modified model is trained by fine-tuning the bottom layers on a target dataset. An adjacency matrix is obtained from the initialized probe unit, and a neural capacitance metric is computed to select an active model for configuring a machine learning system.

Another significant patent is "Model agnostic contrastive explanations for structured data." This invention includes generating contrastive explanations for classifier decisions trained on structured data. It highlights important features that justify decisions and determines a minimal set of new values for features that can alter those decisions.

Career Highlights

Tejaswini has worked with prestigious organizations such as IBM and Rensselaer Polytechnic Institute. Her experience in these institutions has allowed her to develop and refine her innovative ideas in the realm of artificial intelligence and machine learning.

Collaborations

Throughout her career, Tejaswini has collaborated with notable colleagues, including Pin-Yu Chen and Jennifer J Liang. These collaborations have contributed to her success and the advancement of her research.

Conclusion

Tejaswini Pedapati is a pioneering inventor whose work in neural networks and machine learning continues to influence the field. Her innovative patents and collaborations highlight her commitment to advancing technology and improving machine learning systems.