Prehistory — From Neural Networks to the TransformerDan Ciresan et al. (IDSIA)

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition released on arXiv

Why it matters

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

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1003.0358

Added in Week 35, 2026 · See that week

Nearby on the same axis

Understanding the difficulty of training deep feedforward neural networksPaperImageNet holds the first ILSVRCOfficialRectified Linear Units Improve Restricted Boltzmann MachinesOfficialBergstra et al. present TheanoOfficial