scispace - formally typeset
Search or ask a question
Author

Geoffrey E. Hinton

Bio: Geoffrey E. Hinton is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Generative model. The author has an hindex of 157, co-authored 414 publications receiving 409047 citations. Previous affiliations of Geoffrey E. Hinton include Canadian Institute for Advanced Research & Max Planck Society.


Papers
More filters
Journal ArticleDOI
29 Nov 1993
TL;DR: In this paper, the minimum description length principle is used to train the hidden units of a neural network to extract a representation that is cheap to describe but nonetheless allows the input to be reconstructed accurately.
Abstract: The Minimum Description Length principle (MDL) can be used to train the hidden units of a neural network to extract a representation that is cheap to describe but nonetheless allows the input to be reconstructed accurately. We show how MDL can be used to develop highly redundant population codes. Each hidden unit has a location in a low-dimensional implicit space. If the hidden unit activities form a bump of a standard shape in this space, they can be cheaply encoded by the center ofthis bump. So the weights from the input units to the hidden units in an autoencoder are trained to make the activities form a standard bump. The coordinates of the hidden units in the implicit space are also learned, thus allowing flexibility, as the network develops a discontinuous topography when presented with different input classes. Population-coding in a space other than the input enables a network to extract nonlinear higher-order properties of the inputs.

59 citations

Journal ArticleDOI
TL;DR: Two new models that handle surfaces with discontinuities are proposed that develop a mixture of expert interpolators and specialized, asymmetric interpolators that do not cross the discontinUities.
Abstract: We have previously described an unsupervised learning procedure that discovers spatially coherent properties of the world by maximizing the information that parameters extracted from different parts of the sensory input convey about some common underlying cause. When given random dot stereograms of curved surfaces, this procedure learns to extract surface depth because that is the property that is coherent across space. It also learns how to interpolate the depth at one location from the depths at nearby locations (Becker and Hinton 1992b). In this paper, we propose two new models that handle surfaces with discontinuities. The first model attempts to detect cases of discontinuities and reject them. The second model develops a mixture of expert interpolators. It learns to detect the locations of discontinuities and to invoke specialized, asymmetric interpolators that do not cross the discontinuities.

58 citations

Proceedings ArticleDOI
01 May 1995
TL;DR: Glove-TaikII is a system which translates hand gestures-· to speech through an adaptive interface that gives an unlimited vocabulary, multiple languages in addition to direct control of fundamental frequency and volume.
Abstract: Glove-TaikII is a system which translates hand gestures-· to speech through an adaptive interface. Hand gestures are mapped continuously to 10 control parameters of a parallel formant speech synthesizer. The mapping allows the hand to act as an artificial vocal tract that produces speech in real time. This gives an unlimited vocabulary, multiple languages in addition to direct control of fundamental frequency and volume. Currently, the best version of Glove-TaikII uses several input devices (including a Cyberglove, a ContactGlove, a polhemus sensor, and a foot-pedal), a parallel formant speech synthesizer and 3 neural networks. The gestureto-speech task is divided into vowel and consonant production by using a gating network to weight the outputs of a vowel and a consonant neural network. The gating network and the consonant network are trained with examples from the user. The vowel network implements a fixed, user-defined relationship between hand-position and vowel sound and does not require any training examples from the user. Volume, fundamental frequency and stop consonants are produced with a fixed mapping from the input devices. One subject has trained for about 100 hours to speak intelligibly with Glove-TalkII. He passed through eight distinct stages while learning to speak. He speaks slowly with speech quality similar to a text-to-speech synthesizer but with far more natural-sounding pitch variations.

58 citations

Proceedings Article
27 Nov 1995
TL;DR: This work uses a variety of synthetic and real data sets to compare the performance of the wake-sleep algorithm with Monte Carlo and mean field methods for fitting the same generative model and also compares it with other models that are less powerful but easier to fit.
Abstract: The wake-sleep algorithm (Hinton, Dayan, Frey and Neal 1995) is a relatively efficient method of fitting a multilayer stochastic generative model to high-dimensional data. In addition to the top-down connections in the generative model, it makes use of bottom-up connections for approximating the probability distribution over the hidden units given the data, and it trains these bottom-up connections using a simple delta rule. We use a variety of synthetic and real data sets to compare the performance of the wake-sleep algorithm with Monte Carlo and mean field methods for fitting the same generative model and also compare it with other models that are less powerful but easier to fit.

58 citations

Proceedings Article
30 Jul 2005
TL;DR: This work describes a series of progressively better learning algorithms all of which are designed to run on neuron-like hardware and turns a generic network with three hidden layers and 1:7 million connections into a very good generative model of handwritten digits.
Abstract: If neurons are treated as latent variables, our visual systems are non-linear, densely-connected graphical models containing billions of variables and thousands of billions of parameters. Current algorithms would have difficulty learning a graphical model of this scale. Starting with an algorithm that has difficulty learning more than a few thousand parameters, I describe a series of progressively better learning algorithms all of which are designed to run on neuron-like hardware. The latest member of this series can learn deep, multi-layer belief nets quite rapidly. It turns a generic network with three hidden layers and 1:7 million connections into a very good generative model of handwritten digits. After learning, the model gives classification performance that is comparable to the best discriminative methods.

58 citations


Cited by
More filters
Proceedings ArticleDOI
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

123,388 citations

Proceedings Article
01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.

111,197 citations

Proceedings Article
03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

73,978 citations

Journal ArticleDOI
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.

72,897 citations

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

49,914 citations