Public PhD defense Arnout Devos

​[🇺🇸 everything is & will be in English]

​It takes place at EPFL (Lausanne, Switzerland), with more details after registering. A non-technical presentation (30 min) will be followed by an informal apéro to celebrate.

​abstract

​Humans can learn new concepts from only a few examples and quickly adapt to unforeseen circumstances. To this end, they build upon their prior experience and they are prepared to adapt. Most machine learning systems, however, lack the versatility to learn new tasks efficiently and effectively when little data is available. In this talk, I will present my research on developing few-shot machine learning algorithms and applications to adapt machine learning models to new tasks with small data, efficiently and effectively. Next to research, I will also cover my activity in innovation, as an EPFLinnovators fellow in computer science.