
Description
The current research of the Group addresses the development of new
Machine Learning methodologies.
Public datasets and software tools related to the research on Machine Learning recently developed by the group are lisetd below.
Software
 Python implementation for the Contextual Graph Markov Model (CGMM):
CGMM@GitHub by F. Errica.
Related to the paper: D. Bacciu, E. Federico, A. Micheli. Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing.
Proceedings of ICML 2018. Vol. 80. pp. 294303.
Avalaible at Article page .
 Python implementation for the Preterm Infants Survival Assessment (PISA) predictor: PISA@GitHub by M. Podda
Related to the paper: M. Podda, D. Bacciu, A. Micheli, G. Placidi, R. Bellu' L. Gagliardi.
A machine learning approach to estimating preterm infants survival: development of the Preterm Infants
Survival Assessment (PISA) predictor. Scientific Reports, 8(2018). Article Page
 Matlab implementation for the DeepESN (Deep Echo State Network):
DeepESN@MathWorks
by C. Gallicchio.
Related to the papers:
C. Gallicchio, A. Micheli, L. Pedrelli. Deep Reservoir Computing: A Critical Experimental Analysis. Neurocomputing, 2017, vol. 268, pp. 8799, Article page
and
C. Gallicchio, A. Micheli. Deep Echo State Network (DeepESN): A brief survey. arXiv preprint, 2018,
Article arXiv:171204323
 Python implementation for the DeepESN (Deep Echo State Network):
DeepESN@GitHub
by L. Pedrelli.
Related to the papers:
C. Gallicchio, A. Micheli, L. Pedrelli. Deep Reservoir Computing: A Critical
Experimental Analysis. Neurocomputing, 2017, vol. 268, pp. 8799, Article page
and
C. Gallicchio, A. Micheli, L. Pedrelli,
Design of deep echo state networks . Neural Networks, 2018, vol. 108, pp. 3347. Article page.
Data sets
 ARTREE (tree data set)  Artificial Tree Generator: ARTREE page @ CIML
Related to the paper: D. Bacciu, A. Micheli, A. Sperduti. 'Compositional Generative Mapping for TreeStructured Data.Part I: BottomUp Probabilistic Modeling of Trees",
IEEE Transactions on Neural Networks and Learning Systems, vol.23, no.12, pp.19872002, Dec. 2012
 Alkanes Dataset (tree data set):
Alkanes @ CIML
Related to the paper:
A. Micheli. 'Neural Network for Graphs: A Contextual Constructive Approach'.
IEEE Transactions on Neural Networks.
Vol. 20, n. 3, Pages 498511, March 2009. IEEE Inc. ISSN 10459227.
 Indoor User Movement Prediction from RSS data Data Set (sequences): "Indoor" Data Set @ UCI Machine Learning Repository
Related to the paper: D. Bacciu, P. Barsocchi, S. Chessa, C. Gallicchio, and A. Micheli, 'An experimental characterization of reservoir computing in ambient assisted living applications', Neural Computing and Applications, SpringerVerlag, vol. 24 (6), pp. 14511464, ISSN 09410643, 2014.
 Activity Recognition system based on Multisensor data fusion (AReM) (sequences): "AReM" Data Set @ UCI Machine Learning Repository
Related to the paper: F. Palumbo, C. Gallicchio, R. Pucci and A. Micheli, 'Human activity
recognition using multisensor data fusion based on Reservoir Computing',
Journal of Ambient Intelligence and Smart Environments, 2016, 8 (2), pp.
87107.
 Balance Assessment Dataset (sequences):
BalanceDataset @ CIML
Related to the paper: D. Bacciu, S. Chessa, C. Gallicchio, A. Micheli, L. Pedrelli, E. Ferro, L. Fortunati, D. La Rosa, F. Palumbo, F. Vozzi, O. Parodi.
"A learning system for automatic Berg Balance Scale score estimation", Engineering Applications of Artificial Intelligence, vol. 66 (2017), pp. 6074.

 
