KEYNOTE & MASTERCLASS – AI Innovator – Evolve.tech – Crossroads of AI and Hardware
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation and the vision of the Internet-of-Things fuel the interest in resource efficient approaches. These approaches require a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. On top of this, it is crucial to treat uncertainty in a consistent manner in all but the simplest applications of machine learning systems. In particular, a desideratum for any real-world system is to be robust in the presence of outliers and corrupted data, as well as being resource efficient.Data privacy is also an important issue in todays information age. These complex demands are among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology into every day’s applications.
In this master class we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. We provide a review of resource-efficient AI solutions in the field of vision and audio, reducing both computational complexity and memory footprint. In that way, we provide an extensive overview of the current state-of-the-art of robust and efficient machine learning for real-world systems.
Matthias Zöhrer is the CEO and founder of Evolve.tech, a high-tech startup in the field of AI and acoustics.
He is a machine learning specialist working on cutting-edge technology for noise cancellation and speech enhancement. He has a strong background in resource constrained AI systems and machine learning. Matthias Zöhrer has a degree in Telematik at Graz University of Technology, Austria. Since 2013 he is a Research Associate at the Laboratory of Signal Processing and Speech Communication, Graz University of Technology, Austria.