Post-synaptic potential regularization has potential

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 ${\ell }_2$ 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 ${\ell }_2$ regularization in deep architectures trained on CIFAR-10.

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Striving for Simplicity: The All Convolutional Net
• Neural Architecture Search: A Survey
• Regularization for Deep Learning: A Taxonomy

Cited by in corpus (4)

• Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data
• SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks
• Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima
• A non-discriminatory approach to ethical deep learning