Handwriting Recognition with Large Multidimensional Long Short-Term Memory Recurrent Neural Networks
2016pp. 228–233
Citations Over TimeTop 10% of 2016 papers
Abstract
Multidimensional long short-term memory recurrent neural networks achieve impressive results for handwriting recognition. However, with current CPU-based implementations, their training is very expensive and thus their capacity has so far been limited. We release an efficient GPU-based implementation which greatly reduces training times by processing the input in a diagonal-wise fashion. We use this implementation to explore deeper and wider architectures than previously used for handwriting recognition and show that especially the depth plays an important role. We outperform state of the art results on two databases with a deep multidimensional network.
Related Papers
- → Handwriting Recognition using Artificial Intelligence Neural Network and Image Processing(2020)44 cited
- → Handwriting Recognition System- A Review(2019)8 cited
- → A Comprehensive and Comparative Study of Handwriting Recognition System(2023)2 cited
- → Analysis of Signature Handwriting Features and Key Points of Inspection after exercise(2020)
- → A Review of Robust Automated Handwriting Recognition System(2024)