Reading List: Convolutional Neural Networks in Document Recognition, Yann LeCun, 1998

This is the first post in Reading List series where I recap important papers as part of continuing my data science education.

Gradient_Based Learning Applied to Document Recognition by Y. LeCun, L. Bottou, Y. Bengio and P.Haffner.

I start with this paper as it advances a deep learning class that is essentially computers’ vision and hearing, enabling real-life applications such as safe self-driving cars and reading of radiology images.

In discussing solutions to high-dimensional pattern recognition, ie handwritten character or speech, the paper shows that automatic learning machines that operate directly on pixel images are more accurate than hand-crafted individually designed feature extraction modules.

It thus suggested a then-new paradigm of globally trained Graph Transformer Networks, the core of which is a Convolutional Neural Network.

The three conditions that allowed for this progress are: one, low-cost machines with brute-force arithmetic methods; two, large databases for problems with a wide market interest and three, powerful machine learning techniques that can handle high-dimensional inputs and can generate intricate decision functions.


Keywords: Neural Networks, OCR, Document Recognition, Machine Learning, Gradient-Based Learning, Convolutional Neural Networks, Graph Transformer Networks, Finite State Transducers.

comments powered by Disqus
rss facebook twitter github youtube mail spotify instagram linkedin google pinterest medium vimeo