This is a write-up and code tutorial that I wrote for an AI workshop given at UCLA, at which I gave a talk on neural networks and implementing them in Tensorflow. It’s part of a series on machine learning with Tensorflow, and the tutorials for the rest of them are available here.
Recently, I spent sometime writing out the code for a neural network in python from scratch, without using any machine learning libraries. It proved to be a pretty enriching experience and taught me a lot about how neural networks work, and what we can do to make them work better. I thought I’d share some of my thoughts in this post.
Recently, I’ve been going through the Express, Mongoose, and Chai docs in order to help build out and test an API that’s going to be used for ACM Hack, a committee of UCLA’s CS club that focuses on teaching students new technologies and frameworks, as well as fostering/building an environment of hackers and makers at UCLA. We’re completely revamping Hack for the next quarter with regular events, projects, and additional content in terms of blog posts and tutorials for our users. To do this, we needed to revamp the Hack website.
A few thoughts on how machine learning models can be scaled, stored, and used in production applications.
Taking a look at how GraphQL can improve upon the REST paradigm.
Diagnosing medical conditions such as sickle cell disease can become much, much faster.