Neural Networks for Complex Data
It provides a summary of existing work for researchers in machine learning, but is incremental as it does not introduce new methods or findings.
The paper reviews advances in neural network models over the last decade, focusing on their application to complex data types like graphs and functions, but does not present new results or concrete numbers.
Artificial neural networks are simple and efficient machine learning tools. Defined originally in the traditional setting of simple vector data, neural network models have evolved to address more and more difficulties of complex real world problems, ranging from time evolving data to sophisticated data structures such as graphs and functions. This paper summarizes advances on those themes from the last decade, with a focus on results obtained by members of the SAMM team of Université Paris 1