Category Archives: Keras

TensorFlow users on Mac powered by Apple’s new M1/M2 chip can now take advantage of accelerated training using Apple’s Mac-optimized version of TensorFlow 2.4.

The transformers API makes it possible to save all of these pieces to disk at once, saving everything into a single archive in the PyTorch or TensorFlow saved model format.

You can be fairly sure that the model is using two-node binary classification because multi-class classification would have three or more output nodes and one-node binary classification would have one output node

In multi-label classification, we use a binary classifier where each neuron(y_train.shape[1]) in the output layer is responsible for one vs all class classification. binary_crossentropy is suited for binary classification and thus used for multi-label classification.

The ReLU activation function is a default choice for the hidden layers. For the output layer, in general, you will want the logistics activation function for binary classification, the softmax activation function for multiclass classification, and no activation function for regression.

Common deep learning libraries only implement L2 regularization, not the original weight decay. Therefore, on datasets where the use of L2 regularization is beneficial for SGD on many popular image classification datasets, Adam leads to worse results than SGD with momentum for which L2 regularization behaves as expected.

Fraction of the training data to be used as validation data. The Keras will set apart this fraction of the training data. The validation data is selected from the last samples in the x and y data provided.

Stratified train_test_split to maintain the imbalance so that the test and train dataset have the same distribution, then never touch the test set again. Stratified ensure that each dataset split has the same proportion of observations with a given label.

It is for the neural network to learn both deep patterns using the deep path and simple rules through the short path. In contrast, regular MLP forces all the data to flow through the entire stack of layers. These simple patterns in the data may end up being distorted by this sequence of transformations.

The amount of regularization must be balanced for each dataset and architecture. Recognition of this principle permits the general use of super-convergence. Reducing other forms of regularization and regularizing with very large learning rates makes training significantly more efficient.