Deep learning has revolutionized the field of artificial intelligence, and the community has accumulated many classic papers over the years. Below is a list of some of the most influential deep learning papers.
AlexNet (2012)
- This paper introduced the concept of convolutional neural networks (CNNs) for image recognition and won the ImageNet competition by a large margin.
- Read more about AlexNet
VGGNet (2014)
- VGGNet proposed a simple and effective convolutional architecture that was very successful in image classification tasks.
- Learn about VGGNet
GoogLeNet (2014)
- GoogLeNet introduced the inception module, which allowed for a more efficient and deeper network architecture.
- Explore GoogLeNet
ResNet (2015)
- ResNet introduced the concept of residual learning, which made it possible to train very deep networks without the vanishing gradient problem.
- Discover ResNet
DenseNet (2016)
- DenseNet proposed a novel architecture that connects each layer to every other layer in a feed-forward manner, which improves the performance of deep networks.
- Read more about DenseNet
Transformer (2017)
- Transformer introduced self-attention mechanisms for sequence modeling, which has become a key component in many NLP models.
- Learn about Transformer
These papers have laid the foundation for the field of deep learning and continue to inspire new research and applications. If you are interested in diving deeper into the world of deep learning, be sure to check out our Deep Learning Resources.
Images
AlexNet
VGGNet
GoogLeNet
ResNet
DenseNet
Transformer