paper-with-me

홈 › Papers

Scale Normalization

2016-04-26 · Henry Z. Lo, Kevin Amaral, Wei Ding

One of the difficulties of training deep neural networks is caused by improper scaling between layers. Scaling issues introduce exploding / gradient problems, and have typically been addressed by careful scale-preserving initialization. We investigate the value of preserving scale, or isometry, beyond the initial weights. We propose two methods of maintaing isometry, one exact and one stochastic. Preliminary experiments show that for both determinant and scale-normalization effectively speeds up learning. Results suggest that isometry is important in the beginning of learning, and maintaining it leads to faster learning.

📄 PDF Abstract BibTeX arXiv:1604.07796

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bayesian Renormalization

2023-05-17 · David S. Berman, Marc S. Klinger, Alexander G. Stapleton

In this note we present a fully information theoretic approach to renormalization inspired by Bayesian statistical inference, which we refer to as Bayesian Renormalization. The main insight of Bayesian Renormalization is…

Data Compression

Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization

2019-08-31 · Zhuoran Yu, Aojun Zhou, Yukun Ma, Yudian Li 외

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is necessary for fast inference. We show that t…

Data AugmentationImage ClassificationMachine Translation

Diffusion-Guided Renormalization of Neural Systems via Tensor Networks

2025-10-07 · Nathan X. Kodama arxiv

Far from equilibrium, neural systems self-organize across multiple scales. Exploiting multiscale self-organization in neuroscience and artificial intelligence requires a computational framework for modeling the effective…

Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts

2024-09-29 · Dalin Qin, Yehui Li, Weiqi Chen, Zhaoyang Zhu 외

Complex distribution shifts are the main obstacle to achieving accurate long-term time series forecasting. Several efforts have been conducted to capture the distribution characteristics and propose adaptive normalizatio…

Time SeriesTime Series Forecasting

Redefining Self-Normalization Property

2021-01-01 · Zhaodong Chen, Zhao WeiQin, Lei Deng, Guoqi Li 외

The approaches that prevent gradient explosion and vanishing have boosted the performance of deep neural networks in recent years. A unique one among them is the self-normalizing neural network (SNN), which is generally …

Data Augmentation