Lukasz’s research focuses on deep learning applied to natural language processing, and he has recently been working on the use of attention models and transfer learning. Lukasz is a key contributor to Tensor2Tensor, an open-source TensorFlow library containing implementations of several state-of-the-art neural models. He earned a PhD from RWTH Aachen in 2008 and Master’s degrees in mathematics and computer science from the University of Wroclaw in 2003.