Today's machine learning classifiers achieve high performance through a laser-like focus on one and only one task. Humans by contrast, when learning new things, benefit from learning how to do separate but related things. Multi-task learning, which gives machines the ability to learn multiple tasks at once, has many advantages including better performance on complex challenges like virtual drug screening and retinopathy detection. It’s Classification 2.0, opening up multiple new use-cases across industries and making machine learning, a little bit, more like human learning.
Join this webinar as we discuss:
Friederike will also demonstrate a prototype that accompanies Cloudera Fast Forward Labs' newest report and uses MLT (and neural networks) to classify news articles across publications and topics.
Friederike Schüür is a research engineer at Cloudera Fast Forward Labs, where she imagines what applied machine learning in industry will look like in two-years’ time (a time horizon that fosters ambition and yet provides grounding). She dives into new machine learning capabilities and builds fully functioning prototypes that showcase state-of-the-art technology applied to real use cases. She advises clients on how to make use of new machine learning capabilities, from strategy consulting to hands-on collaboration with in-house technical teams. She earned a PhD in cognitive neuroscience from University College London and is a long-time data science for social good volunteer with DataKind.