This is an in-progress list of classic machine learning papers which either introduce a new approach or have a major contribution to the field.
- (1996) A density-based algorithm for discovering clusters in large spatial databases with noise
- (2001) On spectral clustering: Analysis and an algorithm
- (2004) Learning the k in k-means
- (2006) A Fast Learning Algorithm for Deep Belief Nets
- (2008) Extracting and Composing Robust Features with DenoisingAutoencoders
- (2010) Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- (2016) Unsupervised representation learning with deep convolutional generative adversarial networks
- (1986) Experiments on Learning by Back Propagation.
- (2012) Random Search for Hyper-Parameter Optimization
- (2014) Adam: A method for stochastic optimization
- (2014) Dropout: a simple way to prevent neural networks from overfitting
- (2003) Latent Dirichlet Allocation
- (2013) Efficient Estimation of Word Representations in Vector Space
- (2014) Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- (2014) GloVe: Global Vectors for Word Representation
- (2015) Fast R-CNN
- (2016) Bag of Tricks for Efficient Text Classification
- (2016) Deep Residual Learning for Image Recognition
- (2018) AutoAugment: Learning Augmentation Policies from Data
- (2016) Deep Residual Learning for Image Recognition
- (2014) Generative adversarial nets
- (2015) Distilling the Knowledge in a Neural Network
- (2017) Learning to Reason: End-to-End Module Networks for Visual Question Answering
- (2021) Meta Pseudo Labels
- (2021) CKConv: Continuous Kernel Convolution For Sequential Data