In this talk, David Low will be sharing various approaches of building an Artificial Intelligence Chatbot with Deep Learning techniques. Word embedding, Long short-term memory (LSTM) and Sequence-to-Sequence models will be introduced. At the same time, he will present a comparison between the approaches and share a few tips on training deep neural nets optimally. He will also talk about the challenges to build, launch and maintain a chatbot, especially in the financial service industry.
David Low is currently the Co-founder and Chief Data Scientist at Pand.ai. He represented Singapore and National University of Singapore (NUS) in Data Science Game'16 at France and clinched top spot among Asia and America teams. Recently David has been invited as a guest lecturer by NUS to conduct masterclasses on applied Machine Learning and Deep Learning topics. Prior to Pand.ai, he was a Data Scientist with Infocomm Development Authority (IDA) of Singapore. As a pastime activity, he competed on Kaggle and achieved Top 0.2% worldwide ranking.