Articles tagged 'deep learning series'

Hyperparameters and normalization

Hyperparameters There are many hyperparameters that we can fine-tune when training a model. In previous...

Read more...

Weight initialization

Vanishing and exploding gradients The gradient of the loss with respect to any weight is...

Read more...

Backpropagation and the maths behind...

The process of moving the data forward through the network is called forward propagation. Backpropagation...

Read more...

Convolutional networks

A convolutional neural network / CNN / ConvNet is an artificial neural network that detects...

Read more...

Overfitting / underfitting and supervised...

Overfitting and Underfitting Overfitting Overfitting occurs when our model becomes really good at being able...

Read more...

Datasets and predictions

Dataset types The the training dataset is separate from both the validation dataset and the...

Read more...

Loss function and learning rate

Loss function The loss function is what SGD is attempting to minimize by iteratively...

Read more...

Training and learning

Training When we train a neural network, we are trying to optimize the weights associated...

Read more...

Artificial neural networks

An artificial neural network is a computing system that is comprised of a collection of...

Read more...