Skip to content

Next Token다음 조각 Home

Prehistory — From Neural Networks to the TransformerYoshua Bengio et al.Yoshua Bengio2003

A Neural Probabilistic Language Model

A Neural Probabilistic Language Model — JMLR 3, 1137–1155

Why it matters

Proposed a neural language model that learns words as dense vectors. The direct predecessor of the embedding lineage that includes word2vec

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

Officialjmlr.orghttps://www.jmlr.org/papers/v3/bengio03a.html

Added in Week 35, 2026 · See that week

Nearby on the same axis

2006A Fast Learning Algorithm for Deep Belief NetsOfficial Dec 2006Greedy Layer-Wise Training of Deep NetworksPaper 1998Gradient-based learning applied to document recognitionPress 1997Hochreiter and Schmidhuber publish Long Short-Term MemoryOfficial