Synopsis of the PhD Thesis - Network Computations in Artificial Intelligence

Abstract

Traditionally science is done using the reductionism paradigm. Artificial intelligence does not make an exception and it follows the same strategy. At the same time, network science tries to study complex systems as a whole. This synopsis presents my PhD thesis which takes an alternative approach to the reductionism strategy, with the aim to advance both fields, advocating that major breakthroughs can be made when these two are combined. The thesis illustrates this bidirectional relation by: (1) proposing a new method which uses artificial intelligence to improve network science algorithms (i.e. a new centrality metric which computes fully decentralized the nodes and links importance, on the polylogarithmic scale with respect to the number of nodes in the network); and (2) proposing two methods which take inspiration from network science to improve artificial intelligence algorithms (e.g. quadratic acceleration in terms of memory requirements and computational speed of artificial neural network fully connected layers during both, training and inference).