This inventor holds 1 USPTO granted patent. Top assignee: Robert Bosch. Active years: 2025.
Company Filing History:
Years Active: 2025
Title: The Innovative Mind of Liangyu Zhong
Introduction
Liangyu Zhong is a prominent inventor based in Berlin, Germany. He has made significant contributions to the field of image classification through his innovative methods. His work focuses on enhancing the accuracy and efficiency of image classifiers, which are essential in various applications today.
Latest Patents
Liangyu Zhong holds a patent for a method titled "On-the-fly calibration of an image classifier." This invention involves training an image classifier to determine a prediction vector of class probabilities for an input image. The process begins with one or more initial training steps, resulting in current values for the trainable parameters of the image classifier. A training image and its corresponding class label are selected, and a current label vector is determined for training the image classifier. The classifier is applied to the training image based on the current parameter values. If the predicted class matches the class label, the current label vector is established as a soft label based on the prediction vector. A current training step is then performed using this label vector.
Career Highlights
Liangyu Zhong is currently employed at Robert Bosch GmbH, where he continues to develop and refine his innovative ideas. His work at Bosch allows him to collaborate with other talented professionals in the field, further enhancing his contributions to technology.
Collaborations
One of Liangyu Zhong's notable coworkers is Kanil Patel. Together, they work on advancing the capabilities of image classification technologies.
Conclusion
Liangyu Zhong's innovative approach to image classification exemplifies the impact of dedicated inventors in the technology sector. His patent and ongoing work at Robert Bosch GmbH highlight his commitment to advancing this important field.