Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Sergey Ioffe, Christian Szegedy

Published July 2015 · ICML 2015 (32nd International Conference on Machine Learning) · Conference paper

Summary

This paper introduced batch normalization, a technique that normalizes layer inputs using mini-batch statistics to reduce internal covariate shift during training. It allows higher learning rates and less careful initialization, accelerates convergence, and acts as a regularizer. Applied to image classification networks, it dramatically reduced training steps and improved accuracy.

Key findings

Normalizing layer inputs per mini-batch stabilizes and speeds up deep network training.
Enables much higher learning rates and reduces sensitivity to initialization.
Achieved state-of-the-art ImageNet accuracy with far fewer training steps and acted as a regularizer.

Subjects & keywords

Artificial Intelligence batch normalization deep learning neural network training regularization

Cite this paper

APA

Sergey Ioffe, & Christian Szegedy (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML 2015 (32nd International Conference on Machine Learning). https://arxiv.org/abs/1502.03167

BibTeX

@inproceedings{ioffe2015batch,
  author    = {Sergey Ioffe and Christian Szegedy},
  title     = {Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift},
  booktitle = {ICML 2015 (32nd International Conference on Machine Learning)},
  year      = {2015},
  url       = {https://arxiv.org/abs/1502.03167}
}

Related in Artificial Intelligence

AI2023

Segment Anything

Alexander Kirillov, Eric Mintun and Nikhila Ravi

This paper introduces the Segment Anything project: a promptable image segmentation task, the Segment Anything Model (SAM), and the SA-1B dataset. SAM combines an image encoder, a flexible prompt encoder (points, boxes, masks, text), and a fast mask decoder to produce valid segmentation masks from arbitrary prompts. Trained on over 1 billion masks across 11 million images, SAM shows strong zero-shot transfer to many segmentation tasks without additional training.

IEEE/CVF International Conference on Computer Vision (ICCV) Open access

AI2023

GPT-4 Technical Report

OpenAI

This technical report describes GPT-4, a large-scale multimodal Transformer model that accepts image and text inputs and produces text outputs. The report emphasizes that GPT-4 achieves human-level performance on a range of professional and academic benchmarks, and details infrastructure and optimization methods that allowed performance to be predicted from much smaller models. For competitive and safety reasons, the report withholds architecture, dataset, and training details.

arXiv Open access

AI2023

LLaMA: Open and Efficient Foundation Language Models

Hugo Touvron, Thibaut Lavril and Gautier Izacard

The paper presents LLaMA, a family of foundation language models ranging from 7B to 65B parameters trained exclusively on publicly available datasets. It argues that strong performance can be reached without proprietary data and at smaller parameter counts than prior models. LLaMA-13B outperforms the much larger GPT-3 175B on most benchmarks, and LLaMA-65B is competitive with the best contemporary models such as Chinchilla-70B and PaLM-540B.

arXiv preprint (arXiv:2302.13971) Open access