Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs

03/23/2011

∙

The competitive MNIST handwritten digit recognition benchmark has a long history of broken records since 1998. The most recent substantial improvement by others dates back 7 years (error rate 0.4 significantly improve this result, using graphics cards to greatly speed up training of simple but deep MLPs, which achieved 0.35 previous more complex methods. Here we report another substantial improvement: 0.31

READ FULL TEXT

Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs

Massively Deep Artificial Neural Networks for Handwritten Digit Recognition

Comparison and Combination of State-of-the-art Techniques for Handwritten Character Recognition: Topping the MNIST Benchmark

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach

Handwritten Digit Recognition by Elastic Matching

Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets

A new watermarking method to protect blockchain records comprising handwritten files

Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs

Related Research

Massively Deep Artificial Neural Networks for Handwritten Digit Recognition

Comparison and Combination of State-of-the-art Techniques for Handwritten Character Recognition: Topping the MNIST Benchmark

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach

Handwritten Digit Recognition by Elastic Matching

Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets

A new watermarking method to protect blockchain records comprising handwritten files