A New Benchmark Dataset for Handwritten Character Recognition

By L. V. D. van der Maaten. 2009

50 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Wojciech Samek
2. Grgoire Montavon
3. K. Müller
4. Sebastian Lapuschkin
5. Giulia Vilone
6. Alexander Binder
7. Kaushik Roy
8. Christopher J. Anders

Citations in the corpus

• Methods for interpreting and understanding deep neural networks (2017, methodology): “In this example, we would like to explain the prediction of a DNN trained on a handwritten characters dataset [70].”
• Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing (2017, background): “…above-mentioned network denoted by [784 ( 5 × 5 )4c 2s ( 5 × 5 )4c 2s 10o] (CNN containing 784 input neurons, 2 convolutional layers (4c) each followed by a sub-sampling layer (2s), and finally a fully connected layer with 10 output neurons (10o)), for 10 classes (digits 0-9 from TiCH dataset [12]).”