User:MountBrew/sandbox

Ideas for article creation:
Mind potential conflicts of interest! If a conflict of interest exists, follow Articles for creation.


 * Martin Jaggi
 * Mary-Anne Hartley

English article
See my contributions on Talk:Federated learning.

French article
Read first.

German article
Read first.

Training models[edit]

 * What does it mean to train a model? Not necessarily "first gather training data, then do SGD" -> could be RL or stuff, Idk.
 * Training happens once you've specified the type of model, down to the model architecture. This model "type" will have parameters that can be trained. For instance, a neural network has a weight for each edge between two neurons, and a bias for each neuron. These parameters inform how the model output depends on the model input. Training a model is what we call the process of finding "good" values for these parameters. How I write this will depend a lot on the remainder of the article...
 * Overfitting could be part of a list of things to watch out for

Usually, machine learning models require a lot of data in order for them to perform well. Usually, when training a machine learning model, one needs to collect a large, representative sample of data from a training set. Data from the training set can be as varied as a corpus of text, a collection of images, and data collected from individual users of a service. Overfitting is something to watch out for when training a machine learning model. Trained models derived from biased data can result in skewed or undesired predictions.

Federated learning[edit]
Main article: Federated learning

Federated learning is an adapted form of distributed artificial intelligence to training machine learning models that decentralizes the training process, allowing for users' privacy to be maintained by not needing to send their data to a centralized server. This also increases efficiency by decentralizing the training process to many devices. For example, Gboard uses federated machine learning to train search query prediction models on users' mobile phones without having to send individual searches back to Google.

French article
Read first.

German article
Read first.

Level 1 vital articles

 * Read them, improve on-the-spot if I notice something in non-Good articles
 * Is there a similar classification in the French- or German-speaking Wikipedia?