Published inTowards Data ScienceWhere did the Binary Cross-Entropy Loss Function come from?Binary Classification presents a unique problem where: each example(x, y) belongs to one of two complementary classes, each example…Nov 15, 20196Nov 15, 20196
Published inTowards Data ScienceWhy using Mean Squared Error(MSE) cost function for Binary Classification is a bad idea?There are two reasons why MSE is a bad choice for binary classification problems…Nov 14, 20195Nov 14, 20195
How do Tensorflow and Keras implement Binary Classification and the Binary Cross-Entropy function?TensorFlow implements the Binary Cross-Entropy Function in a numerically stable form like this…Nov 14, 20193Nov 14, 20193
Published inTowards Data ScienceNothing but NumPy: Understanding & Creating Binary Classification Neural Networks with…Nothing but Numpy is a continuation of my neural network series. To view the previous blog in this series or for a refresher on neural…Nov 14, 20199Nov 14, 20199
Published inTowards AINothing but NumPy: Understanding & Creating Neural Networks with Computational Graphs from ScratchGet a deep understanding of feedforward neural networks and how to create them.Jun 22, 20197Jun 22, 20197
