paper-with-me

홈 › Papers

Cyclical Learning Rates for Training Neural Networks

2015-06-03 · Leslie N. Smith

It is known that the learning rate is the most important hyper-parameter to tune for training deep neural networks. This paper describes a new method for setting the learning rate, named cyclical learning rates, which practically eliminates the need to experimentally find the best values and schedule for the global learning rates. Instead of monotonically decreasing the learning rate, this method lets the learning rate cyclically vary between reasonable boundary values. Training with cyclical learning rates instead of fixed values achieves improved classification accuracy without a need to tune and often in fewer iterations. This paper also describes a simple way to estimate "reasonable bounds" -- linearly increasing the learning rate of the network for a few epochs. In addition, cyclical learning rates are demonstrated on the CIFAR-10 and CIFAR-100 datasets with ResNets, Stochastic Depth networks, and DenseNets, and the ImageNet dataset with the AlexNet and GoogLeNet architectures. These are practical tools for everyone who trains neural networks.

📄 PDF Abstract BibTeX arXiv:1506.01186

Code (53)

bckenstler/CLR 공식 구현 tf
AlexMGitHub/Checkers-MCTS tf
GPUPhobia/vocal-mask pytorch
GorillaBus/urban-audio-classifier tf
JavClaude/Cyclical-Learning-Rate
JitindraFartiyal/Object-Detection pytorch
Manas2909/Learning-Keras tf
MichaelNasello/nnFromScratch tf
Miltos-90/UNet_Biomedical_Image_Segmentation pytorch
MindSpore-scientific-2/code-4/tree/main/cyclic-cosine-decay-master mindspore
MindSpore-scientific-2/code-9/tree/main/cyclic-cosine-decay-master mindspore
Niteeshaballa/fastai-practice
SevenZhan/Pytorch pytorch
WittmannF/LRFinder
atnlp/reproduced-ml-papers
benihime91/one_cycle_lr-tensorflow tf
benihime91/tensorflow-on-steroids tf
binmishr/Cyclical-learning-rate-with-R-and-Keras tf
brianmanderson/Cyclical_Learning_Rate tf
chandansharma02/Deep_Learning pytorch
coxy1989/clr pytorch
datalass1/fastai tf
davidtvs/pytorch-lr-finder pytorch
delzac/cntk-clr
erasromani/behavior-cloning pytorch
fitushar/Cyclical-Learning-Rates-for-Training-Neural-Networks-With-Unbalanced-Data-Sets
gregtozzi/deep_learning_celnav tf
gurucharanmk/PyTorch_CircularLearningRate pytorch
gurucharanmk/PyTorch_LearningRateFinder pytorch
gurucharanmk/PyTorch_OneCyclePolicyScheduler pytorch
hamiddimyati/dd2424-deep-learning
haritha91/1cycle-Policy-Experiment pytorch
jae1213/CyclicalLR_SGDR pytorch
josequinonez/SkinCancerClassification pytorch
karthikRavichandran/LR_exploration_tf tf
leona-ha/Skin-Screening_Web-App tf
lnsmith54/exploring-loss caffe2
lnsmith54/super-convergence caffe2
locuslab/fast_adversarial pytorch
lrsoenksen/LRFinder tf
m-romanenko/cycliclr tf
maikherbig/AIDeveloper tf
mhmoodlan/cyclic-learning-rate tf
minhncedutw/prac-keras-cyclical-lr
mpyrozhok/adamwr pytorch
nachiket273/One_Cycle_Policy pytorch
nupam/keras-callbacks tf
simon0987/Fast_FGSM pytorch
suhas1999/Flip-kart-grid-challenge pytorch
surmenok/keras_lr_finder
valerkabvv/test_tasks pytorch
yell/kaggle-camera pytorch
ywu94/Code-Notes pytorch

Methods 이 논문이 사용한 방법론

NEW HAMPSHIRE +256777182862 Love spells caster, voodoo spells IN NEW HAMPSHIRE- MANCHESTER, NASHUA 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Inception Module An Inception Module is an image model block that aims to approximate an optimal local sparse structure in a CNN. Put simply, it allows for us to use multiple types of filter…
Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…

Similar Papers 제목 키워드 기반

Deep Reinforcement Learning using Cyclical Learning Rates

2020-07-31 · Ralf Gulde, Marc Tuscher, Akos Csiszar, Oliver Riedel 외

Deep Reinforcement Learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gra…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

General Cyclical Training of Neural Networks

2022-02-17 · Leslie N. Smith

This paper describes the principle of "General Cyclical Training" in machine learning, where training starts and ends with "easy training" and the "hard training" happens during the middle epochs. We propose several mani…

Data AugmentationKnowledge Distillation

Exploring loss function topology with cyclical learning rates

2017-02-14 · Leslie N. Smith, Nicholay Topin

We present observations and discussion of previously unreported phenomena discovered while training residual networks. The goal of this work is to better understand the nature of neural networks through the examination o…

Applying Cyclical Learning Rate to Neural Machine Translation

2020-04-06 · Choon Meng Lee, Jianfeng Liu, Wei Peng

In training deep learning networks, the optimizer and related learning rate are often used without much thought or with minimal tuning, even though it is crucial in ensuring a fast convergence to a good quality minimum o…

Machine TranslationTranslation

Cyclical Curriculum Learning

2022-02-11 · H. Toprak Kesgin, M. Fatih Amasyali

Artificial neural networks (ANN) are inspired by human learning. However, unlike human education, classical ANN does not use a curriculum. Curriculum Learning (CL) refers to the process of ANN training in which examples …

text-classificationText Classification