To compare the previously described approach of hyperparameter tuning using fastai and wandb, today we’ll see how to tackle the same approach, but using PyTorch Lightning instead of fastai. The goal is to have an automated hyperparameter tuning pipeline running on the Numerai data set. What is Numerai? Numerai is a hedge fund which trades stocks in a market neutral fashion. That means that they try to make money without having a lot of risk for their customers.
Today we will try to tackle the Numerai tournament using the fastai deep learning library. However, as the results likely depend on many different hyperparameters, let’s take advantage of the weights and biases library and their sweeps API. Sweeps are hyperparameter runs which test out different combinations of your model’s hyperparameters. What is Numerai? Numerai is a hedge fund which trades stocks in a market neutral fashion. That means that they try to make money without having a lot of risk for their customers.
Label noise in digital Pathology In the field of digital pathology and other health related deep learning applications, label noise is an important challenge to consider during training. It’s inherent to the medical fields as the problems are extremely challenging even for trained experts, so there is high intra- as well as inter-observer variability. This blog post dives into the idea of the paper P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions which is authored by researchers of Microsoft in China.
Label noise introduction Training machine learning models requires a lot of data. Often, it is quite costly to obtain sufficient data for your problem. Sometimes, you might even need domain experts which don’t have much time and are expensive. One option that you can look into is getting cheaper, lower quality data, i.e. have less experienced people annotate data. This usually has the side effect of your labels becoming more noisy.
When you have a big data set and a complicated machine learning problem, chances are that training your model takes a couple of days even on a modern GPU. However, it is well-known that the cycle of having a new idea, implementing it and then verifying it should be as quick as possible. This is to ensure that you can efficiently test out new ideas. If you need to wait for a whole week for your training run, this becomes very inefficient.