The Final Stretch

As I round the corner of the final days of my project, I am striving to succeed in provably demonstrating its practical utility, simplicity and contributions. The neural architecture I have designed so far, however, is anything but simple. It is in fact, notoriously easy to break. Moreover, my objective function is complex and requires some regularization, which increases the hyper-parameter burden. However, I am currently collecting data about how to deploy it efficiently, so I may add an errata section to my final project summary.

It is bittersweet to be so close to the end, but it is also currently a time of perpetual excitement and discovery. I cannot wait to share my final findings.

Tyna Eloundou
Tyna Eloundou

My research interests include alignment (inner and outer variants), safety and AI creativity.