paper-with-me

Papers

An In-depth Study of Stochastic Backpropagation

2022-09-30 · Jun Fang, Mingze Xu, Hao Chen, Bing Shuai, Zhuowen Tu, Joseph Tighe

In this paper, we provide an in-depth study of Stochastic Backpropagation (SBP) when training deep neural networks for standard image classification and object detection tasks. During backward propagation, SBP calculates the gradients by only using a subset of feature maps to save the GPU memory and computational cost. We interpret SBP as an efficient way to implement stochastic gradient decent by performing backpropagation dropout, which leads to considerable memory saving and training process speedup, with a minimal impact on the overall model accuracy. We offer some good practices to apply SBP in training image recognition models, which can be adopted in learning a wide range of deep neural networks. Experiments on image classification and object detection show that SBP can save up to 40% of GPU memory with less than 1% accuracy degradation.

📄 PDF Abstract BibTeX arXiv:2210.00129

Code (1)

amazon-research/stochastic-backpropagation

Tasks

GPUimage-classificationImage Classificationobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs

2018-07-25 · Xiaoran Xu, Songpeng Zu, Yuan Zhang, Hanning Zhou 외

In real-world scenarios, it is appealing to learn a model carrying out stochastic operations internally, known as stochastic computation graphs (SCGs), rather than learning a deterministic mapping. However, standard back…

Reinforcement LearningReinforcement Learning (RL)

Mean field theory for deep dropout networks: digging up gradient backpropagation deeply

2019-12-19 · Wei Huang, Richard Yi Da Xu, Weitao Du, Yutian Zeng 외

In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success. The theory has been applied to various neural network structures, including CNNs, RNNs, Re…

Backpropagation Neural Tree

2022-02-04 · Varun Ojha, Giuseppe Nicosia

We propose a novel algorithm called Backpropagation Neural Tree (BNeuralT), which is a stochastic computational dendritic tree. BNeuralT takes random repeated inputs through its leaves and imposes dendritic nonlinearitie…

DescriptiveImage Classification

RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr

2020-07-07 · ICML 2020 1 · Xingjian Li, Haoyi Xiong, Haozhe An, Cheng-Zhong Xu 외

Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. While the accuracy could be largely improved even when the training…

Transfer Learning

Linear Backpropagation Leads to Faster Convergence

2021-09-29 · Li Ziang, Yiwen Guo, Haodi Liu, ChangShui Zhang

Backpropagation is widely used for calculating gradients in deep neural networks (DNNs). Applied often along with stochastic gradient descent (SGD) or its variants, backpropagation is considered as a de-facto choice in a…

Adversarial Attack