Image for post
Image for post
Photo by Luca Bravo on Unsplash

While I do hate Java, I do have to thank it for getting me back into Python and more importantly, machine learning.

During my Java class, I was introduced to the idea of a sentiment value generator; a way to find out whether or not a word has a positive or negative connotation. In this class, we were not, in fact, using Java to create one of these machines but rather using a list generated by researchers at Stanford in order to rate different reviews.

The idea was that we would loop through all of the words in a review…


Image for post
Image for post
Photo by Cláudio Luiz Castro on Unsplash

The 19th of April marked the end of Ludum Dare’s 46th Game Jam, a competition in which developers are challenged to create a video game in under 72 hours. Even though my team spent the entire weekend frantically coding, animating, and designing, the competition ended up being a ton of fun and overall, an experience that I would highly recommend to anyone interested in game design. Even though we were all rather new to the craft, we were still able to create a product that we were proud of.

This isn’t going to be an inspiring story nor will it…


Image for post
Image for post
Photo by Scott Webb on Unsplash

Recently I had the not so original idea of using tracking enabled Apple’s ARKit in order to create a 6DOF mobile VR experience. After some research partnered with a healthy dose of trial and error, I was able to develop a method that allowed me to do this using Unity. While there are still problems with it, mainly that the experience is somewhat laggy with bugging tracking, I wanted to share the procedure in the hopes that others could replicate it and improve upon it. I personally think that the ability to walk around in mobile VR will help people…


Some common patterns in the ways that I solve problems on the screen and in real life

Image for post
Image for post
Photo by Olav Ahrens Røtne on Unsplash

I‘ve been writing code for a decent period of time, around seven years, and even though I’m not the best at it, it’s changed the way I look at problems in life. As I’ve become better at coding, and solving the problems that come with it, I have begun to see some common patterns in the ways that I solve problems on the screen and in real life.

The Problem Is the Problem

This is by far the biggest thing that I learned while attempting to write my first code, and it’s something I don’t see talked about a lot. When I first started out…


Image for post
Image for post
Photo by JJ Ying on Unsplash

Due to the holiday of Thanksgiving, I ended up taking this week off, and as such, I am once again going to continue my new habit of not writing much.


Image for post
Image for post
Photo by Markus Winkler on Unsplash

Using some of my free time this week, I began to delve into creating a transformer with the Keras functional API. Now, my goal for this week is to actually understand what I am doing. I could try to write a bit more, but for now, the goal is just to keep up the habit.


Image for post
Image for post
Photo by Jad Limcaco on Unsplash

This week was actually pretty amazing. I felt relax and productive at the same time, which is an improvement over usual. The main focus of this week for me was examining BERT transformers. While I had looked at using a transformer architecture for NLP and sentiment classification, it wasn’t clear how I would go about doing this. However, after a bit of research, I discovered that the BERT transformer was created specifically for this purpose. To be honest, I don’t quite understand it yet, but I will definitely report back when I do.

Adios.


Image for post
Image for post
Photo by Avi Waxman on Unsplash

This week was really busy, so I didn’t really manage to do that much. While I hoped to have come back with a big update on a personal project, I wasn’t able to do it. It doesn’t look great or feel great to keep posting nothing updates, but I think it good to be able to continually admit that you failed. Anyway, hopefully this week is better.

Adios


Image for post
Image for post
Photo by Emile Perron on Unsplash

As a result of some unexpected changes in my schedule, I was able to work a little bit on my transformer! Progress has been incredibly slow, but I am proud that I have something to write about. After deciding last week that I was going to write my model using the Hugging Face transformers library, I started this week off by researching how I was going to do that.

First off, I needed to figure out what sort of model I was going to use, as hugging face had a variety of different model types available. After a little bit…


Image for post
Image for post
Photo by Arseny Togulev on Unsplash

This week, I actually managed to make a small amount of progress on my transformer! A bit of better time management enabled me to actually spend valuable time writing code and doing research for my emotion classification transformer. Overall, I complete two main tasks: the first is that I was able to successfully begin managing my data for the transformer and the second is that figured out how I am going to go about creating my NN.

Connor Sparks

👋 My musings here are basically a public stream-of-consciousness journal, so please forgive my writing: it’s getting better, I promise.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store