The market for deep learning applications is predicted to grow at a 65% annual rate in the next 5 years. The growth is fueled by innovative hardware architectures that bring artificial intelligence to devices at the edge of the internet and at its core. Examples include voice assistants, face-based authentication, big data analytics and self-driving vehicles. Established companies as well as numerous semiconductor startups are introducing a diverse range of deep learning IP, and no winner has been declared yet. In this invited session players from industry and academics present their architecture, with programming examples and applications.