Sign in

I am looking at using PyTorch for the machine learning component of one the research projects that I am currently working on. It involves regression with relatively small tabular datasets. The data is produced by computer simulations. Though highly nonlinear there is no noise. I am using shallow (1–2 hidden layers) neural networks for this purpose. This is an atypical use of PyTorch. I did some prototyping with the simpler neural network library from scikit-learn. While the prototype performs as expected scikit-learn does not have GPU support. Hence PyTorch. One question might be why do I need GPU support for…


“Yet things might have gone far otherwise and far worse. When you think of the Battle of Pelennor, do not forget the battles in Dale and the valor of Durin’s Folk. Think of what might have been. Dragon-fire and savage swords in Eriador, night in Rivendell. There might be no Queen in Gondor. We might now hope to return from the victory here to ruin and ash. But that has been averted — because I met Thorin Oakenshield one evening on the edge of spring in Bree. A chance-meeting, as we say in Middle-earth.”

— Gandalf to Frodo and Gimli…

Soham

PhD candidate @IowaStateU in #physics | #Toastmaster | Taming dragons on Sundays. https://soham.dev

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store