CrossQ with weight normalization scales to high update-to-data ratios and matches or outperforms reset-based baselines on 25 continuous control benchmarks.
Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Recently, convolutional neural networks (CNNs) have been used as a powerful tool to solve many problems of machine learning and computer vision. In this paper, we aim to provide insight on the property of convolutional neural networks, as well as a generic method to improve the performance of many CNN architectures. Specifically, we first examine existing CNN models and observe an intriguing property that the filters in the lower layers form pairs (i.e., filters with opposite phase). Inspired by our observation, we propose a novel, simple yet effective activation scheme called concatenated ReLU (CRelu) and theoretically analyze its reconstruction property in CNNs. We integrate CRelu into several state-of-the-art CNN architectures and demonstrate improvement in their recognition performance on CIFAR-10/100 and ImageNet datasets with fewer trainable parameters. Our results suggest that better understanding of the properties of CNNs can lead to significant performance improvement with a simple modification.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
CrossQ with weight normalization scales to high update-to-data ratios and matches or outperforms reset-based baselines on 25 continuous control benchmarks.