AleksandrinunpackRecourse, accountability and feedback loopsRecourse and accountabilityMar 29, 2021Mar 29, 2021
AleksandrinunpackModel ValidationModel validation is the process of evaluating a trained model on test data set. This provides the generalization ability of a trained…Mar 8, 2021Mar 8, 2021
AleksandrinunpackDropout Technique and Ensemble MethodsAbout a decade ago deep learning networks were infamous due to overfitting issue. A fully connected layer occupies most of the parameters…Feb 1, 2021Feb 1, 2021
AleksandrinunpackDecision Trees and Random ForestEnsembles of decision trees (random forests and gradient boosting machines) mainly used for structured data. Although deep learning is…Jan 18, 2021Jan 18, 2021
AleksandrinunpackImproving Our ModelThere’s a range of techniques that we can use to improve our model. The most important is perhaps a learning rate. Our model really needs…Jan 4, 2021Jan 4, 2021