Learning Nonsparse Kernels by Self-Organizing Maps for Structured Data

By Fabio Aiolli, Giovanni Da San Martino, Markus Hagenbuchner, Alessandro Sperduti. 2009

27 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Davide Bacciu
2. Alessandro Sperduti
3. Alessio Micheli
4. Nicoló Navarin
5. Dinh Van Tran
6. Federico Errica
7. Marco Podda

In Computer Vision and Pattern Recognition

1. Alessio Micheli
2. Davide Bacciu
3. Alessandro Sperduti
4. Nicoló Navarin

Citations in the corpus

• Pre-training Graph Neural Networks with Kernels (2018, neutral): “Although there are examples of kernels for structures that can be designed on the basis of a training set [van der Maaten, 2011; Aiolli et al. , 2009; Bacciu et al. , 2018], most of the more efficient and effective graph kernels are based on predefined structural features, i.e, features definition is…”
• Neural Networks for Sequential Data: a Pre-training Approach based on Hidden Markov Models (2015, unknown): “, [24,25]).”
• Generative Kernels for Tree-Structured Data (2018, methodology): “The Activation Mask (AM) kernel [13] constructs an adaptive convolutional kernel from a trained unsupervised recursive neural network for structured data, that is the self-organizing map for structured data (SOM-SD) [40].”