This inventor holds 1 USPTO granted patent. Top assignee: Google Inc.. Active years: 2026.
Company Filing History:
Years Active: 2026
Title: Kun Wang: Innovator in Neural Architecture Search
Introduction
Kun Wang is a prominent inventor based in Pittsburgh, PA (US). He has made significant contributions to the field of machine learning, particularly in the area of neural architecture search. His innovative work has garnered attention for its potential applications in data center machine learning accelerators.
Latest Patents
Kun Wang holds a patent titled "Hybrid and hierarchical multi-trial and OneShot neural architecture search on datacenter machine learning accelerators." This patent describes a hybrid and hierarchical neural architecture search (NAS) approach. The approach includes performing a search space partitioning scheme to divide the search space into sub-search spaces. It further involves executing a first type of NAS, such as a Multi-trial NAS, to cover a search across the sub-search spaces. Additionally, the approach incorporates a second type of NAS, such as a One-Shot NAS, to cover each sub-search space. The method also includes automatically stopping the second type of NAS based on one or more early stopping criteria. Kun Wang has 1 patent to his name.
Career Highlights
Kun Wang is currently employed at Google Inc., where he continues to push the boundaries of innovation in machine learning technologies. His work is instrumental in enhancing the efficiency and effectiveness of neural architecture search methodologies.
Collaborations
Kun Wang collaborates with Garrett Axel Andersen, contributing to advancements in their shared field of expertise.
Conclusion
Kun Wang's innovative contributions to neural architecture search exemplify the impact of dedicated research and development in machine learning. His work at Google Inc. continues to shape the future of technology in this domain.