June 22, 2017

Invited talks


How to design for the unconscious

Matthias Rauterberg

Technische Universiteit Eindhoven

Abstract

We can distinguish human activities in intentional and unintentional, conscious and unconscious, and many more. Most of the modern design in the West is relying on conscious decision making of the user. The challenge in upcoming design is tapping into the unconscious of human behavior. Such kind of design has to rely on input signals beyond human language, e.g. bio-signals, video monitoring, deep learning, etc. The presentation will address the design challenges and shows potential directions into the future.

Slides: How to design for the unconscious

 

Cognitronics: Resource-efficient Architectures for Cognitive Systems

Ulrich Rückert

Bielefeld University

Abstract

In Mapping brain-like structures and processes into electronic substrates has recently seen a revival with the availability of deep-submicron CMOS technology. The basic idea is to exploit the massive parallelism of such circuits and to create low power and fault-tolerant information-processing systems. Aiming at overcoming the big challenges of deep-submicron CMOS technology (power wall, reliability, and design complexity), bio-inspiration offers alternative ways to (embedded) artificial intelligence. The challenge is to understand, design, build, and use new architectures for nanoelectronic systems, which unify the best of brain-inspired information processing concepts and of nanotechnology hardware, including both algorithms and architectures. This talk will give an overview of our experiences in designing brain-inspired architectures for nanoelectronics.

Slides: Cognitronics: Resource-efficient Architectures for Cognitive Systems

 

Towards “Big Data, Weak Label and True Clinical Impact” on Medical Image Diagnosis: The Roles of Deep Label Discovery and Open-ended Recognition

Le Lu

U.S. National Institutes of Health

 

 

Slides: Towards “Big Data, Weak Label and True Clinical Impact” on Medical Image Diagnosis: The Roles of Deep Label Discovery and Open-ended Recognition