Explore >> Select a destination
|
You are here 
|
polukhin.tech | ||
| | | | |
www.ethanrosenthal.com
|
|
| | | | | Talk for TWIMLCon 2022. Abstract It's hard enough to train and deploy a machine learning model to make real-time predictions. By the time a model's out the door, most of us would rather move on to the next model. And maybe that is what most of us do, until a couple months or years pass and the original model's performance has steadily decayed over time. The simplest way to maintain a model's performance is to retrain the model on fresh data, but automating this process is nontrivial. | |
| | | | |
thomascountz.com
|
|
| | | | | Fastai, known for it's MOOCs, is working on a book, Fastbook to go along with their new MOOC starting July 2020. In my eagerness, I've been going through the draft of the book (linked above, though they may remove it after publication) and have been coding alongside on Kaggle. At the end of each chapter of the book is a list of questions for the reader/students to answer. I've found these questions to be rigorous and useful to deepen my understanding. | |
| | | | |
thedarkside.frantzmiccoli.com
|
|
| | | | | The deep learning community has been relying on powerful libraries enabling more than I can dream of in terms of mathematical capabilities. Back in the days, I worked on an artificial neural network project where we implemented the derivatives where we would need them. Seeing those projects made me willing to toy around with their capacities for other models, not necessarily artificial neural... | |
| | | | |
matpalm.com
|
|
| | | |||
