CINECA IRIS Institutional Research Information System
IRIS è il sistema di gestione integrata dei dati della ricerca (persone, progetti, pubblicazioni, attività) adottato dall'Università degli Studi di Torino.
AperTO è l'archivio istituzionale Open Access destinato a raccogliere, rendere visibile e conservare la produzione scientifica dell'Università degli Studi di Torino.
EnglishImproving generalization is one of the main challenges for training deep neural networks on classification tasks. In particular, a number of techniques have been proposed, aiming to boost the performance on unseen data: from standard data augmentation techniques to the ℓ2 regularization, dropout, batch normalization, entropy-driven SGD and many more. In this work we propose an elegant, simple and principled approach: post-synaptic potential regularization (PSP). We tested this regularization on a number of different state-of-the-art scenarios. Empirical results show that PSP achieves a classification error comparable to more sophisticated learning strategies in the MNIST scenario, while improves the generalization compared to ℓ2 regularization in deep architectures trained on CIFAR-10.
| Titolo: | Post-synaptic Potential Regularization Has Potential |
| Autori Riconosciuti: | |
| Autori: | Tartaglione, Enzo; Perlo, Daniele; Grangetto, Marco |
| Data di pubblicazione: | 2019 |
| Abstract: | Improving generalization is one of the main challenges for training deep neural networks on classification tasks. In particular, a number of techniques have been proposed, aiming to boost the performance on unseen data: from standard data augmentation techniques to the ℓ2 regularization, dropout, batch normalization, entropy-driven SGD and many more. In this work we propose an elegant, simple and principled approach: post-synaptic potential regularization (PSP). We tested this regularization on a number of different state-of-the-art scenarios. Empirical results show that PSP achieves a classification error comparable to more sophisticated learning strategies in the MNIST scenario, while improves the generalization compared to ℓ2 regularization in deep architectures trained on CIFAR-10. |
| Editore: | Springer |
| Titolo del libro: | Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning. ICANN 2019 |
| Volume: | 11728 |
| Pagina iniziale: | 187 |
| Pagina finale: | 200 |
| Nome del convegno: | International Conference on Artificial Neural Networks |
| Luogo del convegno: | Munich, Germany |
| Anno del convegno: | 17-19/09/2019 |
| Digital Object Identifier (DOI): | 10.1007/978-3-030-30484-3_16 |
| ISBN: | 978-3-030-30483-6 978-3-030-30484-3 |
| Appare nelle tipologie: | 04A-Conference paper in volume |
File in questo prodotto:
http://hdl.handle.net/2318/1712221
Copyright © 2021