Dropout: A Simple Way to Prevent Neural Networks from Overfitting (2014 · 34,422 citations)
Large neural networks with many parameters easily memorise sampling noise in limited training data, which leads to overfitting.
ImageNet Classification with Deep Convolutional Neural Networks (2012 · 2,801 citations)
The authors worked on image classification from the ImageNet LSVRC-2010 contest. The training set contained about 1.2 million photographs in 1000 classes. They built a deep convolutional network (CNN) with five convolutional and three fully connected layers. The network has approximately 60 million parameters. To…
One weird trick for parallelizing convolutional neural networks (2014 · 1,045 citations)
Training large convolutional networks on several GPUs is limited by communication. Pure data parallelism must exchange many parameters, and pure model parallelism must exchange many activations. Krizhevsky notes that the two layer types behave very differently. Convolutional layers do most of the computation but hold…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

Co-authors here

3 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 4,603 times (of the 149,439 papers whose bibliographies we read); 472 citing papers with a page here →.

Updated 2 November 2026