This tutorial shows how to build a Deep Learning model in H2O for classification and regression problems.

H2O Deep Learning is based on a multi-layer feed-forward artifical neural network that is trained with stochastic gradient descent using back-propragation. The network can contain a large number of hidden layers consisting of neurons with tanh, rectifier and maxout activation functions. Advanced features such as adaptive learning rate, rate annealing, momentum training, dropout, L1/L2 regularization, checkpointing and grid search enable high predictive accuracy. Each compute node trains a copy of the global model parameters on its local data with multi-threading (asynchronously), and contributes periodically to the global model via model averaging across the network.

Vocabulary: