Patrick CallierinSquare Corner BlogComparing Two Forward Feature Selection AlgorithmsSpeed vs. customizabilityAug 8, 2018Aug 8, 2018
Patrick CallierinGab41Introducing source-contrastive estimationLearning deep embeddings for audio source separationJun 15, 2017Jun 15, 2017
Patrick CallierinGab41Feature engineering is just easierYou can’t deep-learn your way out of everything — or you wouldn’t necessarily want to, even if you could.Nov 21, 2016Nov 21, 2016
Patrick CallierinGab41Tell me something I don’t know: Detecting novelty and redundancy with natural language processingIntroducing Pythia, a new Lab41 challengeAug 30, 2016Aug 30, 2016
Patrick CallierinGab41Fits like a GloVe: “Betta” style with dense word vectorsA neural network that has seen over 20 billion words will have a lot to say about them, if you ask nicely.Jun 13, 20161Jun 13, 20161
Patrick CallierinGab41One more reason not to be scared of deep learningJust how data-hungry is deep learning? It is an important question for those of us who don’t have an ocean of data from somewhere like…Mar 10, 2016Mar 10, 2016
Patrick CallierinGab41Some tips for debugging deep learningDeep learning is tricky in several respects. Not only can the math and theory quickly lead to hairballs of gradient formulas and update…Jan 10, 2016Jan 10, 2016