PinnedPublished inTowards Data ScienceSelf Learning AI-Agents Part I: Markov Decision ProcessesA mathematical guide on the theory behind Deep Reinforcement LearningOct 14, 201815Oct 14, 201815
Published inTowards Data ScienceSpeeding Up Training of Neural Networks with Batch-NormalizationOne of the most essential Key-Techniques in Deep LearningMar 28, 2022Mar 28, 2022
Let’s predict Human Behavior with AIUsing Deep Learning to predict how a customer will behave in the futureMar 24, 20222Mar 24, 20222
Underfitting and Overfitting in Deep LearningNot sure if good model… or just overfitting?Jul 18, 2021Jul 18, 2021
Loss Functions in Deep LearningA Guide on the Concept of Loss Functions in Deep Learning — What they are, Why we need them…Mar 7, 2021Mar 7, 2021
Published inTowards Data ScienceActivation Functions in Deep Neural NetworksA Guide on the Theory of Activation Functions in Neural Networks and why we need them in the first place.Mar 1, 20211Mar 1, 20211
Published inDataSeriesArtificial Intelligence Market SizeAnalysis of the Technology of our Future — Trends, Projections, OpportunitiesMar 1, 2021Mar 1, 2021
Published inTowards Data ScienceStochastic-, Batch-, and Mini-Batch Gradient Descent DemystifiedWhy do we need Stochastic, Batch, and Mini Batch Gradient Descent when implementing Deep Neural Networks?Apr 26, 20204Apr 26, 20204
Published inTowards Data ScienceRegularization in Deep Learning — L1, L2, and DropoutA Guide on the Theory and Practicality of the most important Regularization Techniques in Deep LearningFeb 19, 20206Feb 19, 20206
Published inTowards Data ScienceAnomaly Detection with Autoencoders in TensorFlow 2.0A Guide on how to implement Neural Networks in TensorFlow 2.0 to detect anomalies.Jan 14, 20206Jan 14, 20206
