Ueli Meier

Multi-column deep neural networks for image classification

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.

Deep, big, simple neural nets for handwritten digit recognition

Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35 error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.

Flexible, high performance convolutional neural networks for image classification

We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our 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. Test error rates on MNIST drop to 2.42%, 0.97% and 0.48% after 1, 3 and 17 epochs, respectively.

Stacked convolutional auto-encoders for hierarchical feature extraction

We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition (CIFAR10) benchmark.

2012 Special Issue: Multi-column deep neural network for traffic sign classification

We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boosts recognition performance, making the system insensitive also to variations in contrast and illumination.

Convolutional Neural Network Committees for Handwritten Character Classification

In 2010, after many years of stagnation, the MNIST handwriting recognition benchmark record dropped from 0.40% error rate to 0.35%. Here we report 0.27% for a committee of seven deep CNNs trained on graphics cards, narrowing the gap to human performance. We also apply the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters. A committee of seven CNNs obtains the best results published so far for both NIST digits and NIST letters. The robustness of our method is verified by analyzing 78125 different 7-net committees.

A committee of neural networks for traffic sign classification

We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.

Max-pooling convolutional neural networks for vision-based hand gesture recognition

Automatic recognition of gestures using computer vision is important for many real-world applications such as sign language recognition and human-robot interaction (HRI). Our goal is a real-time hand gesture-based HRI interface for mobile robots. We use a state-of-the-art big and deep neural network (NN) combining convolution and max-pooling (MPCNN) for supervised feature learning and classification of hand gestures given by humans to mobile robots using colored gloves. The hand contour is retrieved by color segmentation, then smoothened by morphological image processing which eliminates noisy edges. Our big and deep MPCNN classifies 6 gesture classes with 96% accuracy, nearly three times better than the nearest competitor. Experiments with mobile robots using an ARM 11 533MHz processor achieve real-time gesture recognition performance.

Transfer learning for Latin and Chinese characters with Deep Neural Networks

We analyze transfer learning with Deep Neural Networks (DNN) on various character recognition tasks. DNN trained on digits are perfectly capable of recognizing uppercase letters with minimal retraining. They are on par with DNN fully trained on uppercase letters, but train much faster. DNN trained on Chinese characters easily recognize uppercase Latin letters. Learning Chinese characters is accelerated by first pretraining a DNN on a small subset of all classes and then continuing to train on all classes. Furthermore, pretrained nets consistently outperform randomly initialized nets on new tasks with few labeled data.

Multi-Column Deep Neural Networks for offline handwritten Chinese character classification

Multi-Column Deep Neural Networks achieve state of the art recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human accuracy. This performance is the result of averaging 11-layers deep networks with hundreds of maps per layer, trained on raw, distorted images to prevent them from overfitting. The entire framework runs on a normal desktop computer with a CUDA capable graphics card.