Chang Liu

Title: Chang Liu: Innovator in Deep Learning and Face Recognition Technologies

Introduction

Chang Liu is a prominent inventor based in Medford, MA, known for his contributions to the fields of deep learning and face recognition technologies. With a total of two patents to his name, Liu has made significant strides in enhancing the capabilities of neural networks and improving the accuracy of face recognition systems.

Latest Patents

Liu's latest patents include "Domain generalized margin via meta-learning for deep face recognition" and "Task-aware recommendation of hyperparameter configurations." The first patent presents a method for training a model for face recognition, which involves forward training a batch of samples to create a face recognition model. This method calculates sample weights and updates the model based on gradients obtained from both training and validation batches. The second patent focuses on providing task-aware recommendations for hyperparameter configurations in neural network architectures. It constructs a joint space of tasks and hyperparameter configurations to optimize performance prediction for unseen tasks.

Career Highlights

Throughout his career, Chang Liu has worked with notable companies such as Microsoft Technology Licensing, LLC and NEC Corporation. His experience in these organizations has allowed him to develop innovative solutions that address complex challenges in technology and artificial intelligence.

Collaborations

Liu has collaborated with talented individuals in the field, including Gaurav Mittal and Victor Manuel Fragoso Rojas. These collaborations have contributed to the advancement of his research and the successful development of his patented technologies.

Conclusion

Chang Liu's work in deep learning and face recognition has positioned him as a key figure in the innovation landscape. His patents reflect a commitment to advancing technology and improving the efficiency of neural networks.