Deep learning methods for safety and risk management: Signal processing, video analysis, natural language processing, data reconstruction and beyond.

Speaker:  Dr Nikodem Rybak, Postdoctoral Research Fellow, School of Chemical Engineering, UQ

Abstract:  Deep learning is strongly impacting the development of new sensor systems, particularly computer vision used in process automation and autonomous systems, where it is filling a gap not previously achievable by traditional approaches. Deep learning is also being implemented in the automation of decision support systems. There is a significant scope for the application of the latest deep learning methods to improve operations in mining and mineral processing automation.

Bio:  Dr Nikodem Rybak is a machine learning and computer vision researcher at UQ with more than 10 years of experience in Research and Development. In the last few years he worked on various machine learning problems using deep neural networks as a part of the UQ R!SK research group. Nik previously also worked on natural language processing and constructed state-of-the-art NLP systems for many tasks including knowledge extraction, anomaly detection and categorisation.