James Hodson, Bloomberg AI Research (BRAIN) Lab, New York
Abstract: We are familiar with the generic problems that form the backbone of NLP and AI research, from tokenization and language detection, to Named Entity Recognition (NER), Named Entity Disambiguation (NED), and parsing. These tasks have been codified and are now often viewed as optimization problems over particular sets of training data. We question the formulation of these problems, introduce new and valuable questions, and seek to show that a different approach to this core research could have huge benefits.
Marc Pouly, Lucerne University of Applied Sciences and Arts
Abstract: Eczema are frequent dermatoses with severe health and financial consequences to patients and society. They follow a chronic course and may persist for long periods of time after onset. A new generation of highly effective drugs has recently been pushed onto the market, but due to the exorbitant costs of this new treatment, health insurances cover expenses only in severe cases. Dermatologists have therefore been developing different scoring systems to objectively measure and document eczema severeness. However, assessing the parameters for these scores in practice is difficult as it for example requires to estimate the percentage of body surface with eczema infestation. In this talk we present a prototype-based feasibility study of automated detection and quantification of skin eczema using texton-based imaging and machine-learning techniques; a multi-disciplinary research project between the university hospitals of Zurich and the Lucerne university of applied sciences and arts.
Many thanks to Bloomberg for sponsoring Food and Drinks this time!