Deep Learning

An argument in favor of strong scaling for deep neural networks with small datasets

In this post, I'm writing about my most recent paper, which is joint work with Eduardo R. Rodrigues, Matheus Palhares Viana, and Dario Augusto Borges Oliveira. If you prefer videos, there's a pretty comprehensive version below. You can read the full paper on the arXiv. Apart from all the hype that is certainly involved in Machine Learning, Deep Learning, and Artificial Intelligence these days, there is a lot of very good research being done.

Simple image classification using TensorFlow and CIFAR-10

Almost one year after following cs231n online and doing the assignments, I met the CIFAR-10 dataset again. This time, instead of implementing my Convolutional Neural Network from scratch using numpy, I had to implement mine using TensorFlow, as part of one of the Deep Learning Nano Degree assignments. As an aside, since this course uses some content from the free Deep Learning course, they took the time to fix the sub par presentation of that course.