Artificial intelligence and machine learning. Supervised, unsupervised and reinforced. Symbolic learning Classification and regression models. Optimization of models.

Deep nets. Multilayer networks, backpropagation. Loss functions. Hyperparameters and learning strategies.

Convolutional networks. Recognition of images.

Sequential, recurrent networks. LSTM models.

Paralleling and computation techniques in GPU-based architectures.

Vectorization techniques. Programming with tensorflow and theano.

Scalable automated learning. Parallelization frameworks in computer cluster.

Applications in medicine, finance, automatic driving, etc.