MLST Discord! https://discord.gg/aNPkGUQtc5 Patreon: https://www.patreon.com/mlst Pod: https://anchor.fm/machinelearningstreettalk/episodes/101-DR--WALID-SABA---Extrapolation--Vagueness-and-Behaviorism-e1up2er We had a discussion with Dr. Walid Saba about whether or not MLP neural networks can extrapolate outside of the training support, and what it means to extrapolate in a vector space. Then we discussed the concept of vagueness in cognitive science, for example, what does it mean to be "rich" or what is a "pile of sand"? Finally we discussed behaviourism and the reward is enough hypothesis. Panel: Dr. Tim Scarfe, Dr. Keith Duggar References: A Spline Theory of Deep Networks [Balestriero] https://proceedings.mlr.press/v80/balestriero18b/balestriero18b.pdf The animation we showed of the spline theory was created by Ahmed Imtiaz Humayun (https://twitter.com/imtiazprio) and we will be showing an interview with Imtiaz and Randall very soon! Note that we deleted the final third of the show because it needed some editing for tone, but we went on to discuss: Vagueness Concepts grounded in language