Neural Networks From Scratch

Ilia Karmanov explains neural nets and shows how to build one in R:

Hence, my motivation for this post is two-fold:

  1. Understanding (by writing from scratch) the leaky abstractions behind neural-networks dramatically shifted my focus to elements whose importance I initially overlooked. If my model is not learning I have a better idea of what to address rather than blindly wasting time switching optimisers (or even frameworks).
  2. A deep-neural-network (DNN), once taken apart into lego blocks, is no longer a black-box that is inaccessible to other disciplines outside of AI. It’s a combination of many topics that are very familiar to most people with a basic knowledge of statistics. I believe they need to cover very little (just the glue that holds the blocks together) to get an insight into a whole new realm.

Starting from a linear regression we will work through the maths and the code all the way to a deep-neural-network (DNN) in the accompanying R-notebooks. Hopefully to show that very little is actually new information.

This is pretty detailed.  Karmanov mentions Andrej Karpathy, whose Hacker’s guide to Neural Networks is also a must-read on the topic.

Related Posts

Economic Articles With Data Included

Sebastian Kranz has a Shiny app to help you find economic papers with included data: One gets some information about the size of the data files and the used code files. I also tried to find and extract a README file from each supplement. Most README files explain whether all results can be replicated with […]

Read More

Giving A Name To The R Pipe

John Mount noodles an idea from Hadley Wickham: I’d say this fails on at least two counts, the first “%then%” doesn’t seem grammatical (as d is a noun), and magrittr pipes can’t be associated with a new name (as they are implemented by looking for theirselves by name in captured unevaluated code). However, the wrapr dot arrow pipe can take on new names. […]

Read More


July 2017
« Jun Aug »