High-Performance Neural Networks for Visual Object Classification
The authors present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. The feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. The deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better than more shallow ones. Learning is surprisingly rapid. NORB is completely trained within five epochs.