2010, in 5 pieces

The beginning of a setup in which frameworks determine the speed of research. Influenced the design of later deep learning libraries

An early paper demonstrating the advantages of ReLU, which later became the standard activation function

A standard annual competition in large-scale image classification began. It later became the stage for deep learning's breakthrough

Showed that activation functions and initialization determine training stability. The origin of Glorot initialization

Showed that GPU acceleration alone, without unsupervised pretraining, delivered top performance, reviving the purely supervised learning approach