Instructors: Professor Ole Winther along with company guest lecturers and teaching assistants from DTU Compute.
Machine perception of natural signals has improved a lot in the recent years thanks to deep learning (DL). Improved vision systems with DL will make self-driving cars possible and is leading to more accurate image-based medical diagnosis. Improved speech recognition and natural language processing with DL will lead to many new intelligent applications within health-care and IT. Pattern recognition with DL in large datasets will give new tools for drug discovery, condition monitoring and many other data-driven applications. Applications in other areas such as natural language processing, biology, finance and robotics are numerous. Deep learning is an important tool for the leading IT companies' ambition about becoming machine learning and AI first companies.
The purpose of this course is to teach the participants about the latest developments in the field, about opportunities and pitfalls and give the participating companies access to computational frameworks that will allow them to go directly home and apply into in their own context. It covers both more well-established methods like feed-forward, convolutional and recurrent neural networks and frontiers like un-, semi- and reinforcement learning that can be expected to play a larger role in the coming years. The course is taught by Ole Winther, professor in Data science and complexity, DTU Compute, teaching assistants from DTU Compute with guest lecturers from companies using deep learning. Ole Winther is a deep learning machine learning researcher with experience in teaching deep learning both for DTU students and industry.
Further information
Sign up