Alessandro Mella
Research Subjects
Alessandro Mella has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Massimo Ferri
ARCES and Department of Mathematics, University of Bologna, 40126 Bologna, Italy
2 shared publications - Mattia G. Bergomi
Independent Researcher, 20124 Milan, Italy
2 shared publications - Pietro Vertechi
Ottante, Milan, Italy
2 shared publications
Latest Publications
- Open Access
- 24 March 2023
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 5 (2) , 346-358
Generalized Persistence for Equivariant Operators in Machine Learning
Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines fully aware of data constraints and symmetries. We introduce an original class of neural network layers based on a generalization of topological persistence. The proposed persistence-based layers allow the users to encode specific data properties (e.g., equivariance) easily. Additionally, these layers can be trained through standard optimization procedures (backpropagation) and composed with classical layers. We test the performance of generalized persistence-based layers as pooling operators in convolutional neural networks for image classification on the MNIST, Fashion-MNIST and CIFAR-10 datasets.
- 24 March 2023
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 5 (2) , 346-358
Open AccessGeneralized Persistence for Equivariant Operators in Machine Learning
Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines fully aware of data constraints and symmetries. We introduce an original class of neural network layers based on a generalization of topological persistence. The proposed persistence-based layers allow the users to encode specific data properties (e.g., equivariance) easily. Additionally, these layers can be trained through standard optimization procedures (backpropagation) and composed with classical layers. We test the performance of generalized persistence-based layers as pooling operators in convolutional neural networks for image classification on the MNIST, Fashion-MNIST and CIFAR-10 datasets.
- Open Access
Persistence-based operators in machine learning
Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines fully aware of data constraints and symmetries. We introduce a class of persistence-based neural network layers. Persistence-based layers allow the users to easily inject knowledge about symmetries (equivariance) respected by the data, are equipped with learnable weights, and can be composed with state-of-the-art neural architectures.
Open AccessPersistence-based operators in machine learning
Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines fully aware of data constraints and symmetries. We introduce a class of persistence-based neural network layers. Persistence-based layers allow the users to easily inject knowledge about symmetries (equivariance) respected by the data, are equipped with learnable weights, and can be composed with state-of-the-art neural architectures.