Hey there, fellow machine learning enthusiasts! I’m thrilled to share with you a remarkable breakthrough in ML research. As an undergraduate student, I’ve developed a novel algorithm that combines DRTP and No-Prop to achieve an astonishing 91.25% accuracy on the MNIST dataset using only one hidden layer – and it’s all written in pure C.
This achievement is particularly exciting because, to the best of my knowledge, it’s a world-first. I’ve made the code publicly available on GitHub, and I’d love for you to take a look, provide feedback, and help me refine my work. Your input will be invaluable in shaping my research paper and, hopefully, securing an internship in ML research or engineering.
Take a look at the repo: https://github.com/JaimeCasanovaCodes/DRTP-NOPROP-C. Let’s push the boundaries of ML together!