Abhijit S Mudigonda

Title: Abhijit S Mudigonda: Innovator in Deep Neural Networks

Introduction

Abhijit S Mudigonda is a prominent inventor based in Cambridge, MA (US). He has made significant contributions to the field of artificial intelligence, particularly in the area of deep neural networks. His innovative work focuses on enhancing the efficiency of neural network models.

Latest Patents

Abhijit holds a patent for "Restructuring deep neural networks to reduce the number of parameters." This patent describes techniques for minimizing the number of parameters in a deep neural network model. The invention involves a device that includes a memory for storing computer executable components and a processor for executing these components. A structure extraction component determines the number of input nodes associated with a fully connected layer of the model. Additionally, a transformation component replaces the fully connected layer with sparsely connected sublayers, which have fewer connections than the original layer. The number of these sublayers is based on a defined decrease in the number of input nodes.

Career Highlights

Abhijit is currently employed at International Business Machines Corporation, commonly known as IBM. His work at IBM has allowed him to explore and develop advanced techniques in machine learning and artificial intelligence.

Collaborations

Some of his notable coworkers include Dan Gutfreund and Quanfu Fan. Their collaborative efforts contribute to the innovative projects at IBM.

Conclusion

Abhijit S Mudigonda is a key figure in the advancement of deep neural networks, with a focus on reducing complexity while maintaining performance. His contributions are paving the way for more efficient AI systems.