Efficient Machine Learning
Modern AI suffers from ever-increasing costs in time, infrastructure and energy. Efficient methods requiring less data and computation are paramount for the economical viability of projects using ML in companies of all sizes, and, crucially, for an ecologically responsible development of society.

Series in this AoI

Data valuation

Attributions of value to training samples can be used to examine data, improve data acquisition, debug and improve models or compensate data providers. Recent developments in the field enable principled and useful definitions of value which overcome the computational cost of previous approaches.

Data efficiency

Numerous applications of Machine Learning in business intelligence, process optimization, product development or sales do not benefit from true “big data”. Blind application of state-of-the-art methods can lead to catastrophic failure. Proper data acquisition and modelling are key to successful applications.