Home page

Deconstructing Deep Learning + ╬┤eviations

Drop me an email | RSS feed link : Click
Format : Date | Title
  TL; DR

Total number of posts : 89

Go To : PAPERS o ARTICLES o BOOKS o SPACE

View My GitHub Profile


Go to index

Defining the project and outlining what is to come in the future

Reading time : ~1 min

by Subhaditya Mukherjee

An introduction to what I want to do and why.

Why do I need to make a library from scratch when there are so many out there?

Simply put, I want to learn. And what better way to learn then by making something from scratch?

Another reason is that documenting the whole process will allow me to learn a lot more than I knew and will help anyone who follows this to see the process, successes and failures of the process.

What do I have in mind?

I will be using Julia for this and the project will probably span as long as I keep working on it. Which hopefully will be for a long time. In the process, I will try to document what I have done, and why and explore challenges and try to implement many things along the way. Note that this is not meant to be a library which you can use right now. It is a playground.

Can I add to it?

Feel free to fork the project and add it to your version of the code. I do not get anything out of this except learning and sharing it with the community.

Can I talk to you about Deep Learning?

YES! I would love to do that. Drop me an email at msubhaditya@gmail.com and we can talk about it. :)

Related posts:  FP16  AI Superpowers Kai Fu Lee  Digital Minimalism Cal Newport  More Deep Learning, Less Crying - A guide  Super resolution  Federated Learning  Taking Batchnorm For Granted  A murder mystery and Adversarial attack  Thank you and a rain check  Pruning