2012 IEEE Conference on Computer Vision and Pattern Recognition (2012)
Providence, RI USA
June 16, 2012 to June 21, 2012
J. Schmidhuber , IDSIA-USI-SUPSI, Manno-Lugano, Switzerland
U. Meier , IDSIA-USI-SUPSI, Manno-Lugano, Switzerland
D. Ciresan , IDSIA-USI-SUPSI, Manno-Lugano, Switzerland
Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. Our biologically plausible, wide and deep artificial neural network architectures can. Small (often minimal) receptive fields of convolutional winner-take-all neurons yield large network depth, resulting in roughly as many sparsely connected neural layers as found in mammals between retina and visual cortex. Only winner neurons are trained. Several deep neural columns become experts on inputs preprocessed in different ways; their predictions are averaged. Graphics cards allow for fast training. On the very competitive MNIST handwriting benchmark, our method is the first to achieve near-human performance. On a traffic sign recognition benchmark it outperforms humans by a factor of two. We also improve the state-of-the-art on a plethora of common image classification benchmarks.
neural nets, graphics processing units, handwritten character recognition, image classification, image recognition, learning (artificial intelligence), traffic sign recognition benchmark, multicolumn deep neural networks, image classification, computer vision, machine learning, human performance, handwritten digits recognition, traffic signs, artificial neural network architectures, convolutional winner-take-all neurons, retina, visual cortex, sparsely connected neural layers, graphics cards, fast training, MNIST handwriting benchmark, Training, Error analysis, Neurons, Computer architecture, Benchmark testing, Graphics processing unit
J. Schmidhuber, U. Meier and D. Ciresan, "Multi-column deep neural networks for image classification," 2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Providence, RI USA, 2012, pp. 3642-3649.