Category Archive

Episode Summary: Leo Boytsov, a PhD researcher from the Language Technologies Institute of Carnegie Mellon University, talks about fast approximate search in modern information retrieval. We discuss the curse of dimensionality, hard-to-beat baselines and NMSLIB, Leo's super fast library for nearest-neighbour search. How does NMSLIB compare to Facebook's FAISS and Spotify's Annoy? Warning: very technical. Links & resources: NMSLIB: Leonid's ...

Episode Summary: Andreas Müller talks about how he fell in love with scikit-learn and his continuous work there as the package maintainer. We also cover his work at Amazon and why he left to work on open source; his recent book on machine learning in Python; sustainability and future of sklearn in the "deep learning world", and his impressions of ...

Episode Summary: A few years ago I promised you a blog series on how to start your own consulting business in machine learning: getting set up, figuring out legal & intellectual property rights, finding consistent work, scoping in the face of research uncertainty, the project life cycle, mistakes to avoid... I gave a few talks on this topic but never ...

Episode Summary: Today I sat down with Tomáš Mikolov, my fellow Czech countryman whom most of you will know through his work on word2vec. But Tomáš has many more interesting things to say beside word2vec (although we cover word2vec too!): his beginnings with 8bit graphics and games, living in NY compared to California, AI research at Microsoft vs Google vs ...