ARTIFICIAL NEURAL NETWORKS AND DEEP LEARNING

Synthetic program:

Neural networks are mature, flexible, and powerful non-linear data-driven models that have successfully solved many complex tasks in science and engineering. The advent of the deep learning paradigm, i.e., training (neural) networks to simultaneously learn an optimal data representation and a model solving the requested task, has further boosted neural networks research and development. These models nowadays achieve human-like performance in natural language processing, text modeling, gene expression modeling, and image recognition, to name a few examples. This course provides a broad introduction to artificial neural networks (ANN), starting from the traditional feedforward (FFNN) and recurrent (RNN) neural networks architectures, till the most successful deep-learning models including convolutional neural networks (CNN) and long short-term memories (LSTM). The course aims at providing students with a theoretical background and the practical skills to understand and use ANN and, at the same time, become familiar and with Deep Learning for solving complex engineering problems.