Spatially-sparse convolutional neural networks
This addresses efficiency and performance issues in deep learning for tasks like online handwriting recognition and image classification, though it is incremental as it builds on existing CNN methods by leveraging sparsity.
The paper tackled the problem of training deep convolutional neural networks under budget and time constraints by developing a CNN for spatially-sparse inputs, achieving a test error of 3.82% on the CASIA-OLHWDB1.1 dataset and reducing errors to 6.28% on CIFAR-10 and 24.30% on CIFAR-100.
Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks. Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn with a one-pixel wide pen on a high resolution grid looks like a sparse matrix. Taking advantage of the sparsity allowed us more efficiently to train and test large, deep CNNs. On the CASIA-OLHWDB1.1 dataset containing 3755 character classes we get a test error of 3.82%. Although pictures are not sparse, they can be thought of as sparse by adding padding. Applying a deep convolutional network using sparsity has resulted in a substantial reduction in test error on the CIFAR small picture datasets: 6.28% on CIFAR-10 and 24.30% for CIFAR-100.