A
Alessio Micheli
Researcher at University of Pisa
Publications - 219
Citations - 5013
Alessio Micheli is an academic researcher from University of Pisa. The author has contributed to research in topics: Reservoir computing & Recurrent neural network. The author has an hindex of 33, co-authored 205 publications receiving 3770 citations. Previous affiliations of Alessio Micheli include University of Padua.
Papers
More filters
Journal ArticleDOI
Neural Network for Graphs: A Contextual Constructive Approach
TL;DR: The new model allows the extension of the input domain for supervised neural networks to a general class of graphs including both acyclic/cyclic, directed/undirected labeled graphs and can realize adaptive contextual transductions, learning the mapping from graphs for both classification and regression tasks.
Journal ArticleDOI
Deep reservoir computing: A critical experimental analysis
TL;DR: It turns out that a deep layering of recurrent models allows an effective diversification of temporal representations in the layers of the hierarchy, by amplifying the effects of the factors influencing the time-scales and the richness of the dynamics, measured as the entropy of recurrent units activations.
Proceedings Article
A Fair Comparison of Graph Neural Networks for Graph Classification
TL;DR: By comparing GNNs with structure-agnostic baselines the authors provide convincing evidence that, on some datasets, structural information has not been exploited yet and can contribute to the development of the graph learning field, by providing a much needed grounding for rigorous evaluations of graph classification models.
Journal ArticleDOI
A Gentle Introduction to Deep Learning for Graphs
TL;DR: The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing and introduces the basic building blocks that can be combined to design novel and effective neural models for graphs.
Journal ArticleDOI
Design of deep echo state networks
TL;DR: This paper addresses a fundamental open issue in deep learning, namely the question of how to establish the number of layers in recurrent architectures in the form of deep echo state networks (DeepESNs), and provides a novel approach to the architectural design of deep Recurrent Neural Networks using signal frequency analysis.