/tags/fast.ai/ Recent content in fast.ai on Mari Galicer. Hugo -- gohugo.io en-us Wed, 23 Jan 2019 21:42:42 +0000 /posts/stochastic-gradient-descent/ Wed, 23 Jan 2019 21:42:42 +0000 /posts/stochastic-gradient-descent/ In the last third of the lesson 2 video, Jeremy goes into detail about linear regression and stochastic gradient descent. I found this part of the lesson really helpful, so I took some in depth notes! If you want to follow along interactively, all the code that I refer to in this post can be found in the Fast.ai repo. Building a dataset First, we need to create some fake data points that we will later try to apply the techniques of SGD to. /posts/setting-up-fast-ai-rc-cluster/ Sun, 13 Jan 2019 23:46:37 +0000 /posts/setting-up-fast-ai-rc-cluster/ RC’s community cluster is a great resource to take advantage of! I had a rough time getting the Fast AI course set up, so I wrote down some instructions (hopefully) help others save some time. Make an account on recurse.com/settings/cluster - this requires setting up and copying over an SSH key instructions here. SSH onto one of the GPU-enabled machines - I chose to use mercer (both Mercer and Crosby have powerful graphics cards). /posts/fast-ai-week-1/ Fri, 11 Jan 2019 21:16:12 +0000 /posts/fast-ai-week-1/ During my time at the Recurse Center, I’m taking a machine learning course via Jeremy Howard’s Fast.ai - “Practical Deep Learning for Coders.” What attracted me to this course over others (like Andrew Ng’s Coursera course) was the top-down learning approach: the structure is hands on building models first, and diving into the theory later. Most of the computer science classes I’ve taken in the past have taken on the opposite structure, to my frustration.