InAI AdvancesbyValeria Fonseca Diaz·Aug 20, 2024AI is like magic, it’s not really magicMagic is not really magic, it’s just too fastA response icon1A response icon1
InTowards AIbyValeria Fonseca Diaz·Aug 2, 2024Natural Selection for AIDid it evolve, or did we create it?A response icon1A response icon1
InTDS ArchivebyValeria Fonseca Diaz·Sep 1, 2023Tidying Up the Framework of Dataset Shifts: The ExampleHow the conditional probability changes as a function of the three probability elementsA response icon3A response icon3
InTDS ArchivebyValeria Fonseca Diaz·Jul 18, 2023Tidying up the framework of dataset shiftsTaking a step back about the causes of model degradation
InMV LearnbyValeria Fonseca Diaz·Jul 3, 2023Thriving: A survival guide to you PhDFrom daydreaming to effective choicesA response icon1A response icon1
InTowards AIbyValeria Fonseca Diaz·May 28, 2023AI is officially born. What will we do with it?How can we learn to adapt faster? That’s our biggest inquiry.A response icon1A response icon1
InTDS ArchivebyValeria Fonseca Diaz·May 11, 2023The Lifetime of a Machine Learning ModelWhen are they born and how do they transform?A response icon3A response icon3
InTDS ArchivebyValeria Fonseca Diaz·Apr 6, 2023Model employment: The inference comes after training, not duringTraining and using models are two separate phases
InTDS ArchivebyValeria Fonseca Diaz·Feb 2, 2023Prediction Performance Drift: The Other Side of the CoinWe know the causes, let’s talk about the typesA response icon1A response icon1
InTDS ArchivebyValeria Fonseca Diaz·Apr 16, 2022Is Interpreting ML Models a Dead-End?The interpretation process can be detached from the model architectureA response icon3A response icon3