ImageNet Classification with Deep Convolutional Neural Networks

Authors: Krizhevsky, A., Sutskever, I., & Hinton, G. E. Year: 2012 ArXiv: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks

Summary

AlexNet demonstrates that deep convolutional neural networks trained on GPUs can dramatically outperform hand-engineered features on ImageNet. This work sparked the deep learning revolution in computer vision.

Key Concepts

• Deep CNN architecture with 8 layers
• GPU acceleration for training
• Dropout for regularization
• ReLU activation functions
• Data augmentation techniques

Impact

AlexNet won ImageNet 2012 with a massive margin over traditional methods, proving deep learning's superiority. It launched the era of deep CNNs and GPU-accelerated training.

Related Papers

• VGG: Very Deep Convolutional Networks
• ResNet: Deep Residual Learning

---

Citation:

@inproceedings{krizhevsky2012imagenet,
  title={ImageNet classification with deep convolutional neural networks},
  author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
  booktitle={Advances in neural information processing systems},
  pages={1097--1105},
  year={2012}
}