Neural Networks: recent advances - Deep learning - and some (mathematical ?) problems. Rui Alberto Pimenta Rodrigues (Faculdade de Ciências e Tecnologia, Universidade Nova).
Abstract: (Deep) Neural networks seem to be achieving the targets drawn for Artificial Intelligence in the early 60's. We will present the practical accomplishments.
The underlying mathematical models will be discussed:
-Feed forward neural networks
-Recurrent neural networks
-Generative neural networks (Boltzmann Machines, Variational AutoEncoders, Generative Adversary Networks) .
All these models have sometimes millions of parameters that are learned (estimated) from examples (training data). The learning procedure will be discussed. Training data is always a small fraction of real data where these models are applied. To avoid overfitting the model parameters to training data, and poor generalization to large real data, regularization techniques are used.