InTDS ArchivebyZ Singer·Aug 29, 2019Beyond the Derivative — SubderivativesMachine Learning relies heavily on differentiable functions, but that’s rarely the case in practice. What can we do instead?A response icon1A response icon1
InTDS ArchivebyZ Singer·Jun 25, 2019Topological Data Analysis — Unpacking the BuzzwordSeriously, what the heck is Topological Data Analysis? A concrete explanation with pictures and words.A response icon2A response icon2
InTDS ArchivebyZ Singer·Jun 22, 2019Basics of Independent Component AnalysisA decomposition tool that humans are naturally good at, but don’t think about.A response icon2A response icon2
InTDS ArchivebyZ Singer·Jun 18, 20193 Quick Tips for Training ML ModelsYour model won’t converge. Help.
InTDS ArchivebyZ Singer·May 6, 2019Softmax and UncertaintyThe softmax function carries a probabilistic interpretation in neural networks. When does this interpretation break down and mislead…A response icon1A response icon1
InTDS ArchivebyZ Singer·Mar 25, 2019Why Norms Matters — Machine LearningThere are countless names and uses for the L¹ and L² norms — but what do they really represent and how are they different?A response icon3A response icon3
InTDS ArchivebyZ Singer·Jan 25, 2019Understanding Machine Learning on Point Clouds through PointNet++Point clouds are a convenient way of representing spatial data and other unordered data. But what are they, and how are they used in ML?A response icon5A response icon5
InTDS ArchivebyZ Singer·Jan 7, 2019Manifolds in Data Science — A Brief OverviewManifolds are an essential tool for representing data in higher dimensions. But what are manifolds, and how are they used?A response icon10A response icon10
InTDS ArchivebyZ Singer·Dec 28, 2018Understanding High Dimensional Spaces in Machine LearningHigh dimensional spaces are everywhere in machine learning. How can we think about these spaces in a concrete way?A response icon2A response icon2