Company Filing History:
Years Active: 2022
Title: Zhilin Yang: Innovator in Neural Network Technologies
Introduction
Zhilin Yang is a prominent inventor based in Pittsburgh, PA (US). He has made significant contributions to the field of artificial intelligence, particularly in the development of neural network technologies. His innovative work has led to the creation of a patent that enhances the efficiency of neural networks.
Latest Patents
Zhilin Yang holds a patent titled "Computationally efficient expressive output layers for neural networks." This patent encompasses methods, systems, and apparatus, including computer programs encoded on computer storage media, for incorporating a computationally efficient expressive output layer in a neural network. The output layer is designed to map a received hidden state to a probability distribution over a vocabulary of possible outputs. It generates a respective context embedding for each of a plurality of gates from the hidden state. For each possible output in the vocabulary, it computes a gated logit by applying an output embedding for the possible output to the weighed sum. Finally, it generates the probability distribution over the vocabulary of possible outputs by applying a softmax to the gated logits.
Career Highlights
Zhilin Yang is currently employed at Google Inc., where he continues to push the boundaries of technology and innovation. His work at Google has allowed him to collaborate with some of the brightest minds in the industry.
Collaborations
Some of Zhilin Yang's notable coworkers include Thang Minh Luong and Quoc V Le. Their collaborative efforts contribute to the advancement of neural network technologies and artificial intelligence.
Conclusion
Zhilin Yang's contributions to neural network technologies exemplify the spirit of innovation in the tech industry. His patent reflects a significant advancement in the efficiency of neural networks, showcasing his expertise and dedication to the field.