Good Morning/Afternoon/Evening to you! My name is Blake Gella and I am a Master of Science in Electrical and Computer Engineering Graduate from UCLA. I am currently searching for new grad positions as a machine learning engineer in the Greater San Francisco Bay Area and the Greater Sacremento Area. While I am searching for a job, I will be posting about my projects, tutorials, and other interesting topics in the field of machine learning and computer vision on my personal website. I hope you enjoy my content and feel free to reach out to me on LinkedIn or via email if you have any questions or just want to chat!

Projects

You can find all of my projects on my github. The main projects I have worked on are:

• EEG Classification and Diffusion - A project that classifies EEG signals using different variations of CNNs. We also explore the efficacy of using diffusion to generate EEG signals. We find that 1D signals are very easy to overfit using a diffusion model, meaning a simpler model like a GAN would be a better fit for our method. The project is mainly focused on the paper that we produced after finishing it. The notebook with all the experiments can be found on the github repo, but it is not cleaned up (I will clean it up soon).
• Schedule Sender - This is a project that I initiated when I was working at the UCLA Housing as front desker. The project is a scraper that scrapes the Google Sheets schedule and sends it to the front desk workers. It was an idea that I pitched to management and resulted in a 10% decrease in missed shifts. The project is slightly messy, as I had to constantly adapt to the changing structure of the schedules they sent. I currently have the framework up in case any housing worker wants to maintain the project. I also have my general thoughts on how to improve the project in the future.

Tutorials

I am currently working on a series of tutorials on computer vision algorithms and applications. The series will go over the general theory behind many computer vision algorithms (classical and deep learning), as well as example demos on how to use these algorithms in practice. All code will be linked at the end in a Python Notebook, which can be tested in Google Colab. I am also planning on building a github repo for all of these algorithms and demos, so stay tuned for that in the future!