You are here

Scaling Up Deep Learning for NLP

Dr. Jonathan Shihao Ji
Associate Professor, GSU
Thursday, February 1, 2018 - 5:30pm to 6:30pm
Student Center East Room 217

In this talk, I will talk about some of my recent research in the area of deep learning for NLP, especially how to scale up deep NLP algorithms through approximation and HPC techniques. I will show that with appropriate approximation techniques, we can not only speed up the training of deep learning algorithms but also improve their predictive accuracy. Typical deep learning NLP algorithms, such as word2vec, neural language modeling, and neural machine translation will be covered.

Speaker's Bio: 

Dr. Jonathan Shihao Ji is an Associate Professor in the CS department at Georgia State University. His principal research interests lie in the area of machine learning and deep learning with an emphasis on high-performance computing. He is interested in developing efficient algorithms that can learn from a variety of data sources (e.g., image, audio, and text) on a large scale and automate decision-making processes in dynamic environments. Dr. Ji received his PhD in Electrical and Computer Engineering from Duke University in 2006. After that he was an research associate at Duke for about 1.5 years. Prior to joining GSU, he spent about 10 years in industry research labs.