Jorgen Peddersen

Title: Jorgen Peddersen: Innovator in Convolutional Neural Network Applications

Introduction

Jorgen Peddersen is a notable inventor based in Kensington, Australia. He has made significant contributions to the field of technology, particularly in the optimization of memory for Convolutional Neural Network (CNN) applications. With a total of 4 patents to his name, Peddersen's work is at the forefront of advancing computational efficiency in modern systems.

Latest Patents

Peddersen's latest patents include innovative methods for configuring a System-on-Chip (SoC) to execute CNN processes. One of his patents focuses on layer-based operations scheduling to optimize memory for CNN applications. This method involves receiving scheduling schemes, selecting a scheme for the current layer, and determining the current state of memory for storing feature map data. It also includes selecting candidate scheduling schemes for the next layer based on the current memory state.

Another significant patent addresses memory access optimization using per-layer computational mapping and memory allocation for CNN applications. This method determines memory access requirements, expresses them as relationships describing data reusability, and combines these with the costs of memory operations. The goal is to minimize external memory access for each CNN layer, thereby enhancing the overall efficiency of the process.

Career Highlights

Jorgen Peddersen is currently employed at Canon Kabushiki Kaisha, where he continues to develop innovative solutions in the field of technology. His work has garnered attention for its practical applications in improving the performance of CNNs, which are crucial in various artificial intelligence tasks.

Collaborations

Peddersen has collaborated with talented individuals such as Sridevan Parameswaran and Haseeb Bokhari. These collaborations have contributed to the advancement of their shared goals in technology and innovation.

Conclusion

Jorgen Peddersen's contributions to the field of Convolutional Neural Networks demonstrate his commitment to innovation and efficiency. His patents reflect a deep understanding of the complexities involved in memory optimization and computational processes. Through his work at Canon Kabushiki Kaisha, he continues to push the boundaries of technology, making a lasting impact in the industry.