Backpropagation Implementation and Gradient Checking Approximate implementation of backpropagation without regularization using NumPy, and Gradient Checking for the Derivatives. machine-learning andrew-ng

Backpropagation Derivation The post delves into the mathematics of how backpropagation is defined. It has its roots in partial derivatives and is easily understandable andrew-ng machine-learning mathematics

Neural Networks: Cost Function and Backpropagation Intuition behind the idea of backpropagation and its extension to calculate cost function machine-learning andrew-ng

Neural Networks Intuition The relationship between logistic regression and neural networks. Explaination about how neural network is the logical successor of logistic regression machine-learning andrew-ng

Neural Networks Theory An Artificial Neural Network is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information machine-learning andrew-ng

Non-linear Hypotheses Advantages of neural networks over logistic regession and the relationship between the two. Neural network is essentially the successor of logistic regression. machine-learning andrew-ng

Regularized Logistic Regression Regularization is a process of introducing additional information in order to solve an ill-posed problem or to prevent overfitting machine-learning andrew-ng

Regularized Linear Regression Regularization is a process of introducing additional information in order to solve an ill-posed problem or to prevent overfitting machine-learning andrew-ng

Overfitting and Regularization Overfitting occurs when a model is excessively complex, such as having too many parameters relative to the number of observations machine-learning andrew-ng