Publications
Export 5 results:
Filters: Author is Scardapane, Simone [Clear All Filters]
, "Kafnets: Kernel-based non-parametric activation functions for neural networks", Neural Networks, vol. 110, pp. 19-32, February, 2019.
, "Complex-valued Neural Networks with Non-parametric Activation Functions", IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 3, issue 1, 2018.
, "Recursive multikernel filters exploiting nonlinear temporal structure", 25th European Signal Processing Conference (EUSIPCO 2017), Kos, Greece, August, 2017.
PDF Version (290.2 KB)
PDF Version (290.2 KB), "Recurrent Neural Networks With Flexible Gates Using Kernel Activation Functions", IEEE International Workshop on Machine Learning for Signal Processing, Aalborg, Denmark, IEEE, September, 2018.
, "Improving Graph Convolutional Networks with Non-Parametric Activation Functions", 26th European Signal Processing Conference (EUSIPCO 2018), Rome, Italy, EURASIP, September, 2018.
Disclaimer
These publications are included to facilitate downloads to those people asking for copies for personal use. Some of this material is published at copyrighted journals or conference proceedings, so personal use of the download is required. In particular publications from IEEE should be downloaded according to the following IEEE note:
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.