2013, in 3 pieces
3 records · 0 notes
December 2
Diederik P. Kingma, Max Welling
Kingma and Welling publish Auto-Encoding Variational Bayes on arXiv
Made it possible to train probabilistic generative models with backpropagation, becoming one pillar of the generative model lineage
Volodymyr Mnih et al. (DeepMind)
DeepMind publishes Playing Atari with Deep Reinforcement Learning on arXiv
An early case showing that deep reinforcement learning works from screen input alone
January 1
Tomas Mikolov et al. (Google)
Mikolov et al. at Google present word2vec
The starting point of every dense retrieval and embedding stack that followed