Neural Network Techniques Quiz

A technique used in artificial neural networks (ANNs) that involves normalizing the inputs of each layer by re-centering and re-scaling them. This helps stabilize the training process and reduces overfitting.

A technique used in ANNs to prevent overfitting by randomly dropping nodes or connections during training. This forces the network to become more robust and less reliant on specific features.

The size of the training dataset used in each iteration of the learning process. It determines how many examples are used to update the network's weights in each step.

One complete pass through the entire training dataset. It represents one cycle where the network has seen all the training examples.

A technique used in machine learning to prevent overfitting and improve the generalization ability of the model. It involves adding a penalty term to the loss function, which discourages the model from becoming too complex.

A technique that normalizes the inputs of each layer in a neural network by re-centering and re-scaling them, stabilizing training and reducing overfitting.

This method prevents overfitting by randomly dropping nodes or connections during training, forcing the network to be less reliant on specific features.

The number of training examples used in each iteration of the weight learning process. Think of a mini-batch of examples.

A complete cycle where the neural network has seen all the training data. This is affected by the batch size.

A process of adding information to a learning model to prevent overfitting and improve generalization. Examples include L1 and L2 regularization.