ÂÜÀòÂÒÂ×

Albert Zeyer is AppTek's lead machine learning architect for the development of the core software framework as well as research on neural networks. He finished his PhD in the Human Language Technology Group at RWTH Aachen University, Germany under the supervision of Prof. Hermann Ney. He received both his M.Sc. in Mathematics and M.Sc. in Computer Science from RWTH Aachen University in 2013. His research is focused on neural networks including general support of AppTek's ASR, Neural MT and NLU technologies. The beginning of his first studies and passion for neural networks and connectionism goes back to 1996. Topics of his recent work include recurrent networks, attention models, and end-to-end models in general, with applications in speech recognition, translation and language modeling. Albert started developing software in 1995, and has published a variety of Open Source projects and many peer reviewed publications since. The Tensorflow based software RETURNN, which he has developed as the main architect for his PhD research, plays a central role in Apptek HLT.