Wait, am I the only one who didn't know scikit-learn and XGBoost can do continual learning?!
Continual learning is where you update a model as new data comes in. Not by retraining the model from scratch (old data + new data). This is great if you're dealing with huge data where retraining on the entire dataset would be computationally painful.
Has anyone used this before? What cool uses could this unlock in your projects?
I didn’t know you could update those models in place, either!
I imagine this is especially useful when the model is slow to train and data that is particularly “relevant” (in the sense that including it confers a noticeable and important performance increase in terms of whatever it is that the model is doing) arrives continuously while the model is in production (such that retraining introduces unwanted downtime).
I would be interested to hear about use cases for this, too.
No account yet? Create an account
Enter your username or e-mail address. We'll send you an e-mail with instructions to reset your password.
