paper-with-me

홈 › Papers

Is Feature Diversity Necessary in Neural Network Initialization?

2019-12-11 · Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry

Standard practice in training neural networks involves initializing the weights in an independent fashion. The results of recent work suggest that feature "diversity" at initialization plays an important role in training the network. However, other initialization schemes with reduced feature diversity have also been shown to be viable. In this work, we conduct a series of experiments aimed at elucidating the importance of feature diversity at initialization. We show that a complete lack of diversity is harmful to training, but its effects can be counteracted by a relatively small addition of noise - even the noise in standard non-deterministic GPU computations is sufficient. Furthermore, we construct a deep convolutional network with identical features at initialization and almost all of the weights initialized at 0 that can be trained to reach accuracy matching its standard-initialized counterpart.

📄 PDF Abstract BibTeX arXiv:1912.05137

Code (1)

yanivbl6/fixup 공식 구현 pytorch

Tasks

DiversityGPU

Similar Papers 제목 키워드 기반

Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?

2020-07-02 · ICML 2020 1 · Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of …

DiversityGPU

A Survey on Activation Functions and their relation with Xavier and He Normal Initialization

2020-03-18 · Leonid Datta

In artificial neural network, the activation function and the weight initialization method play important roles in training and performance of a neural network. The question arises is what properties of a function are im…

RelationSurvey

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior

2026-06-01 · Xiang Li, Dianbo Liu, Kenji Kawaguchi arxiv

Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse. Existing strategies for enhancing diversity predominantly focus on intervening during the generation trajectory. We identif…

Self-supervised Assisted Active Learning for Skin Lesion Segmentation

2022-05-14 · Ziyuan Zhao, Wenjing Lu, Zeng Zeng, Kaixin Xu 외

Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements. Recently, active learning (AL) strategies strive to reduce annotation costs by …

Active LearningDiversityImage SegmentationLesion Segmentation+4

Enhancing Diversity in Multi-objective Feature Selection

2024-07-25 · Sevil Zanjani Miyandoab, Shahryar Rahnamayan, Azam Asilian Bidgoli, Sevda Ebrahimi 외

Feature selection plays a pivotal role in the data preprocessing and model-building pipeline, significantly enhancing model performance, interpretability, and resource efficiency across diverse domains. In population-bas…

Diversityfeature selection