InTDS ArchivebySamuele MazzantiWhat Is Better: One General Model or Many Specialized Models?Comparing the effectiveness of training several ML models specialized on different groups, versus training one unique model for all the…Dec 30, 202268010Dec 30, 202268010
InTDS ArchivebyPiero PaialungaHands-on Generative Adversarial Networks (GAN) for Signal Processing, with PythonHere’s how to build a generative Deep Learning model for Signal Processing in a few lines of codeDec 27, 20225626Dec 27, 20225626
InTDS ArchivebyChristian LeschinskiAre you interpreting your logistic regression correctly?Why regression coefficients alone do not tell you what you need to know to understand your modelJul 5, 20222481Jul 5, 20222481
InSyncedReviewbySyncedNeurIPS 2022 | Meta AI, Stanford & Tübingen U Beat Neural Scaling Laws via Data PruningStudies on various machine learning models have shown that applying neural scaling laws — increasing compute, model size, and pretraining…Nov 29, 202271Nov 29, 202271
InTDS ArchivebyEduardo BlancasCan I Trust My Model’s Probabilities? A Deep Dive into Probability CalibrationA practical guide on probability calibrationNov 10, 2022256Nov 10, 2022256
InGeek CulturebyMicropredictionOptimizing a Portfolio of ModelsIn this colab notebook I provide an example of the use of the precise Python package (and PyPortfolioOpt) to create a diversified portfolio…Feb 16, 2022104Feb 16, 2022104
InTDS ArchivebyAnna ArakelyanHidden Data Science Gem: Rainbow Method for Label EncodingMake stronger and simpler models by leveraging natural orderOct 29, 20223907Oct 29, 20223907
Sergey LevineAn Ecological Perspective on Reinforcement LearningIt has nothing to do with rainforests, at least not necessarily. J. J. Gibson’s seminal work “The Ecological Approach to Visual Perception”…Dec 15, 20211192Dec 15, 20211192