This event was recorded on Crowdcast. We're working on editing the recording, but until then you can view the full recording on Crowdcast by clicking the button below.
Gradient descent is the algorithm at the heart of many machine learning problems. In this talk, I’ll introduce the algorithm and code it up from scratch to apply it to a toy linear regression problem on the relationship between videogame metacritic scores and sales.
Software Engineer at Heap
Matt Dupree is a wannabe philosophy professor turned wannabe tech entrepreneur. He’s currently a software engineer at a YC-backed product analytics company called “Heap.” You can find out more about him here: https://www.philosophicalhacker.com/