Machine Learning using the Nvidia Jetson Nano

The Nvidia Jetson Nano is a small embedded compute board with
four CPU cores and a 128-core Maxwell generation GPU.
We utilize the PyTorch framework to train a convolutional neural network image classifier
using a small imaging subset of the VLA Sky Survey that is split
into both testing and validation collections. We contruct a simple shape classification
scheme and report on the loss function for the network that can be run on the Nano hardware.


Theme – Machine Learning, Statistics, and Algorithms