Classic Paper Review: Generating Complex Sequences and Handwriting with LSTMs

shaneguML · x · 2026-08-13

A look back at Alex Graves' seminal 2013 paper, Generating Sequences With Recurrent Neural Networks. The research demonstrates how Long Short-Term Memory (LSTM) recurrent neural networks can generate complex sequences with long-range structure by predicting one data point at a time.

The approach is validated on both text (discrete data) and online handwriting (real-valued data). It is further extended to handwriting synthesis by conditioning the network's predictions on a text sequence, enabling the generation of highly realistic cursive handwriting in a wide variety of styles.

Original post →

More from Research

Research channel →