John Gookassian

Title: The Innovative Contributions of John Gookassian

Introduction

John Gookassian is a notable inventor based in Mountain View, CA (US). He has made significant contributions to the field of photomask manufacturing through his innovative patent. His work focuses on utilizing artificial neural networks to enhance the modeling process, which has implications for the semiconductor industry.

Latest Patents

John Gookassian holds a patent titled "Method of modeling e-beam photomask manufacturing process using image-based artificial neural networks." This patent describes a method where an image-based Artificial Neural Network (ANN) is employed for photomask modeling. The ANN can self-construct an internal representation of the photomask manufacturing process, which alleviates the constraints posed by traditional mathematical and statistical tools. This innovation significantly reduces the effort required from model-builders, making the process more efficient and cost-effective. The ANN model necessitates mask layout data to be converted into image pixel form. During the training phase, a first circuit image and its existing SEM image are modeled through multiple layers of convolution and rectification to extract key features. In the testing phase, a second circuit image is compared to ensure it meets predetermined requirements before being converted back to circuit layout data for photomask writing.

Career Highlights

John Gookassian is currently employed at Synopsys, Inc., where he continues to push the boundaries of innovation in his field. His work has garnered attention for its potential to streamline photomask manufacturing processes, which are critical in the production of semiconductors.

Collaborations

Throughout his career, John has collaborated with talented individuals such as Parikshit Kulkarni and Dan Hung. These collaborations have contributed to the advancement of technology in photomask modeling and manufacturing.

Conclusion

John Gookassian's innovative approach to photomask manufacturing through artificial neural networks exemplifies the impact of modern technology on traditional processes. His contributions are paving the way for more efficient manufacturing methods in the semiconductor industry.