paper-with-me

홈 › Papers

What's Hidden in a Randomly Weighted Neural Network?

2019-11-29 · CVPR 2020 6 · Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari

Training a neural network is synonymous with learning the values of the weights. By contrast, we demonstrate that randomly weighted neural networks contain subnetworks which achieve impressive performance without ever training the weight values. Hidden in a randomly weighted Wide ResNet-50 we show that there is a subnetwork (with random weights) that is smaller than, but matches the performance of a ResNet-34 trained on ImageNet. Not only do these "untrained subnetworks" exist, but we provide an algorithm to effectively find them. We empirically show that as randomly weighted neural networks with fixed weights grow wider and deeper, an "untrained subnetwork" approaches a network with learned weights in accuracy. Our code and pretrained models are available at https://github.com/allenai/hidden-networks.

📄 PDF Abstract BibTeX arXiv:1911.13299

Code (4)

allenai/hidden-networks 공식 구현 pytorch
julianscher/SLTN-GA pytorch
kosnil/signed_supermasks tf
x-zho14/hidden-networks pytorch

Tasks

Image Classification

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Weight Decay 설명 없음
SGD with Momentum 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Adam 설명 없음
Wide Residual Block 설명 없음
WideResNet 설명 없음

Similar Papers 제목 키워드 기반

What’s Hidden in a One-layer Randomly Weighted Transformer?

2021-11-01 · EMNLP 2021 11 · Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer 외

We demonstrate that, hidden within one-layer randomly weighted neural networks, there exist subnetworks that can achieve impressive performance, without ever modifying the weight initializations, on machine translation t…

Machine TranslationTranslation

What's Hidden in a One-layer Randomly Weighted Transformer?

2021-09-08 · Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer 외

We demonstrate that, hidden within one-layer randomly weighted neural networks, there exist subnetworks that can achieve impressive performance, without ever modifying the weight initializations, on machine translation t…

Machine TranslationTranslation

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently

2021-09-29 · ICLR 2022 4 · Xiaohan Chen, Jason Zhang, Zhangyang Wang

Sparse neural networks (NNs) are intensively investigated in literature due to their appeal in saving storage, memory, and computational costs. A recent work (Ramanujan et al., 2020) showed that, different from conventio…

Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks

2021-11-24 · Ángel López García-Arias, Masanori Hashimoto, Masato Motomura, Jaehoon Yu

Deep neural networks (DNNs) are so over-parametrized that recent research has found them to already contain a subnetwork with high accuracy at their randomly initialized state. Finding these subnetworks is a viable alter…

J-Net: Randomly weighted U-Net for audio source separation

2019-11-29 · Bo-Wen Chen, Yen-Min Hsu, Hung-Yi Lee

Several results in the computer vision literature have shown the potential of randomly weighted neural networks. While they perform fairly well as feature extractors for discriminative tasks, a positive correlation exist…

Audio Source SeparationDecoder