LeCun, Y., Bottou, L., Bengio, Y., Ha#ner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11) (1998) 2278--2324 Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
First 50 documents Next 50
Unknown - Pe Cep Ua (2002) (Correct)
....are bio inspired hierarchical multi layered neural network approaches that model to some degree characteristics of the human visual cortex and encompass scale and translation invariant feature detection layers. Convolutional neural networks have been successfully applied for character recognition [5], object detection [5] and more speci cally for the task of face recognition [3] 2 Convolutional Neural Networks Figure 1 shows the architecture of the convolutional neural networks we trained for the task of facial expression recognition. Its layers alternate between convolution layers with ....
....multi layered neural network approaches that model to some degree characteristics of the human visual cortex and encompass scale and translation invariant feature detection layers. Convolutional neural networks have been successfully applied for character recognition [5] object detection [5] and more speci cally for the task of face recognition [3] 2 Convolutional Neural Networks Figure 1 shows the architecture of the convolutional neural networks we trained for the task of facial expression recognition. Its layers alternate between convolution layers with feature maps ConvLay ....
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, November 1998.
An Analytical Handwritten Word Recognition System.. - Tay, Lallican.. (Correct)
....level training. The recognition performances of the globally trained system are compared to the baseline system. 1. Introduction Most of today s state of the art cursive word recognizers combine the discriminative power of NNs with the excellent capacity of modeling sequences provided by HMMs [1, 2, 3, 4, 5]. The role of the NN in these hybrid systems is to provide probabilities for character hypothesis or sub character entities, whereas the HMM is used to model the sequence of observations and to compute word likelihoods, usually based on a lexicon. This approach often yields better recognition ....
....optimal recognition performance at the word level. Furthermore, character level training implies that we need to provide examples of characters as well as non characters ( junk ) to train the NN, which is not an easy task [3] Word level discriminant training seems to be an answer to our problem [2, 4, 5]. Instead of generating isolated characters from the word images in order to train the NN separately, we instantly back propagate the error at the word level into the NN to update its parameters. All transition probabilities in the HMMs are set to 1 and are not modified during training (see Fig. ....
Y.LeCun, L.Bottou, Y.Bengio, P.Haffner, "Gradient-Based Learning Applied to Document Recognition", Proceedings of IEEE, Vol. 86, No. 11, pp. 2278-2324, 1998.
Meter Value Recognition using Locally Connected Hierarchical.. - Behnke (2003) (Correct)
....of entire meter value blocks. forward Neural Abstraction Pyramid [1, 2, 3] consisting of five layers. This architecture is characterized by its hierarchical structure and its local connectivity with weight sharing. It has similarities to the Neocognitron [4] and to convolutional networks [5], like LeNet 5 or SDNNs. In contrast to classifiers sliding over an input line, it processes the entire meter value block in parallel. The bottom Layer 0 has a resolution of 3216. It contains only the input array. Resolution decreases from layer to layer by a factor of two in both dimensions, ....
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proc. of IEEE, 86(11):2278--2324, 1998.
Relational Sequential Inference with Reliable Observations - Fern, Givan (Correct)
....assumption than reliable observations due to the fixed window size. Finding a good state inference function is problematic here because of the ambiguity at transitions our FGM technique can be viewed as varying the window size to avoid the ambiguities at transition points. Other work, such as [6, 8], uses observation subsequence classifiers to construct an optimization problem. Each classification assigns some measure of good fit (with the classified subsequence) to each state, and then an optimization problem is solved to select a specific state sequence. These methods have all assumed a ....
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
A Two-Stage System For Meter Value Recognition - Behnke (2003) (Correct)
....is sketched in Fig. 4. It is a feed forward Neural Abstraction Pyramid [1, 2, 3] consisting of five layers. This architecture is characterized by its hierarchical structure and its local connectivity with weight sharing. It has similarities to the Neocognitron [4] and to convolutional networks [5], like LeNet 5 or SDNNs. In contrast to classifiers sliding over an input line, it processes the entire meter value block in parallel. The bottom Layer 0 has a resolution of 3216. It contains only the input array. Resolution decreases from layer to layer by a factor of two in both dimensions, ....
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition, " Proc. of IEEE, vol. 86(11), pp. 2278--2324, 1998.
Incremental Gaussian Processes - Quiñonero-Candela, Winther (Correct)
....experiments because of its high memory requirements. This is the reason why we only ran the comparison for up to 2400 training example for the Mackey Glass data set. To illustrate the performance in classification problems we choose a very large data set, the MNIST database of handwritten digits [19], with 60000 training and 10000 test images. The images are of size 28 28 pixels. We use PCA to project them down to 16 dimensional vectors. We only perform a preliminary experiment consisting of a one against all binary classification problem to illustrate that Bayesian approaches to ....
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278--2324, November 1998.
Face Localization in the Neural Abstraction Pyramid - Behnke (2003) (Correct)
....to L 2 (16 8) L 3 contains 10 excitatory and 5 inhibitory features. The network s connectivity is recurrent and local. The weights of all cells of a feature array are described by a co mb n tem55 te. Such weight sharing has been used in the Neocognitron [5] and in convolutional neural networks [8] to reduce the num ber of free paramD)# s. Each feature cell receives input from only a s m ll window of cells that correspond to sim5E r locations in the layer below (forward weighs) in the sam e layer (lateral weights) and from the layer above (backward weights) Weights from excitatory cells ....
Y. LeC un, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proc.ofIEEE, 86(11):2278--2324, 1998.
Loss Functions for Discriminative Training of Energy-Based.. - Yann Lecun And (2005) (1 citation) Self-citation (Lecun) (Correct)
No context found.
Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, November 1998.
Automatic Recognition of Handwritten Numerical Strings - Oliveira (2003) (3 citations) Self-citation (Bengio) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haner. Gradient-based learning applied to document recognition. Procs of IEEE, 86(11):22782324, 1998.
Discriminative Techniques for the Recognition of Complex-Shaped .. - Carmichael (2003) Self-citation (Lecun) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, November 1998.
Automatic Recognition of Handwritten Numerical Strings - Oliveira (2003) (3 citations) Self-citation (Bengio) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haner. Gradient-based learning applied to document recognition. Procs of IEEE, 86(11):22782324, 1998.
Torch: A Modular Machine Learning Software Library - Collobert, al. (2002) (14 citations) Self-citation (Bengio) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):22782324, November 1998.
Unsupervised Learning of Image Recognition - With Neural Society (Correct)
No context found.
LeCun, Y., Bottou, L., Bengio, Y., Ha#ner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11) (1998) 2278--2324
Finite Iteration DT-CNN - New Design and Operating.. - Merkwirth, Bröcker.. (2004) (Correct)
No context found.
Y. LeCun et al, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278--2324, 1998.
Stochastic Gradient Descent Training of Ensembles - Of Dt-Cnn Classifiers (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, P. Ha#ner, "Gradient-based learning applied to document recognition",Proceedings of the IEEE 86, 11, 2278--2324, 1998
Searching for Character Models - Jaety Edwards Uc (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Finite Iteration DT-CNN with Stationary Templates - Wichard, Ogorzalek.. (2004) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278--2324, 1998. [Online]. Available: citeseer.nj.nec.com/lecun98gradientbased.html
Journal of Machine Learning Research 7 (2006) 1437--1466 .. - Tobias Glasmachers.. (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Inferring Motor Programs from Images of - Handwritten Digits Geoffrey (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, November 1998.
Pattern Recognition Using Finite-Iteration Cellular Systems - Ogorzalek, Merkwirth, al. (2005) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278--2324, 1998. [Online]. Available: citeseer.nj.nec.com/lecun98gradientbased.html
Robust Face Detection Based on Convolutional Neural - Networks Delakis And (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-Based Learning Applied to Document Recognition. Intelligent Signal Processing, pp. 306-351, 2001.
Online and Offline Character Recognition Using Alignment.. - Jonathan Alon Vassilis (2005) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradientbased learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Unknown - (2005) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradientbased learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Query-Sensitive Embeddings - Athitsos, Hadjieleftheriou, Kollios, .. (2005) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Learning Euclidean Embeddings for Indexing and.. - Athitsos, Alon.. (2004) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Shape Matching and Object Recognition Using Shape Contexts - Belongie, Malik, Puzicha (2001) (69 citations) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, November 1998.
Biologically-Inspired Face Detection.. - Christian Siagian.. (Correct)
No context found.
Lecun, Y., L. Bottou, Y. Bengio, and P. Haffner, "Gradient Based Learning Applied to Document Recognition," Proceedings to IEEE 86(11), 2278 - 2324. 1998. 7
Learning Euclidean Embeddings for Indexing and.. - Athitsos, Alon.. (2004) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
A Majority Voting Scheme for Multiresolution Recognition.. - Bhattacharya, Chaudhuri (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradientbased learning applied to document recognition", Proceedings of the IEEE, vol. 86(11),
Coupling of a local vision by Markov field and a global.. - Choisy, Belaïd (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradientbased learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Support Vector Machines for Handwritten Numerical String.. - Oliveira, Sabourin (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Procs of IEEE, 86(11):2278--2324, 1998.
Using Character Recognition and Segmentation to Tell.. - Patrice Simard Richard (2003) (1 citation) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
Incremental Gaussian Processes - Quiñonero-Candela, Winther (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," in Poceedings of the IEEE, 1998, vol. 86, pp. 2278--2324.
Learning Structure and Concepts in Data Through Data Clustering - Hamerly (2003) (Correct)
No context found.
Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Ha ner. Gradientbased learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.
Robust Face Detection Based on Convolutional Neural - Networks Delakis And (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-Based Learning Applied to Document Recognition. Intelligent Signal Processing, pp. 306-351, 2001.
Local Context in Non-linear Deformation Models for.. - Keysers, Gollan, Ney (2004) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner. Gradient-Based Learning Applied to Document Recognition. Proc. of the IEEE, 86(11):2278--2324, Nov. 1998.
Pattern Recognition, Neighborhood Codes, and Lattice Animals - Jyh (2000) (1 citation) (Correct)
No context found.
Y. Bengio Y. Lecun, L. Bottou and P.Haffner. Gradient-based learning applied to document recognition. Proc. of the IEEE, 86(11):2278--2324, 1998.
Benchmarks for Storage and Retrieval in Multimedia Databases - Forsyth (Correct)
No context found.
Y. Lecun, L. Bottou, Y. Bengio, and P. Ha#ner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE 86(11), pp. 2278--2324, 1998.
A Generic Approach For Image Classification Based On.. - Maree, Geurts.. (2004) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradientbased learning applied to document recognition," Proc. of the IEEE, vol. 86, no. 11, pp. 2278--2324, 1998.
Automatic Recognition of Handwritten Dates on Brazilian Bank.. - Morita (2003) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haner. Gradient-based learning applied to document recognition. Proc. of IEEE, 86(11):22782324, 1998.
Learning the K in K-Means - Hamerly, Elkan (2003) (4 citations) (Correct)
No context found.
Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Learning Euclidean Embeddings for Indexing and.. - Athitsos, Alon.. (2004) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Using Character Recognition and Segmentation to.. - Simard, Szeliski, .. (2003) (1 citation) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
Probability Estimates for Multi-class Classification by.. - Wu, Lin, Weng (2003) (7 citations) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha#ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, November 1998. MNIST database available at http://yann.lecun.com/exdb/mnist/.
Best Practices for Convolutional Neural Networks - Applied To Visual (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, "Gradient-based learning applied to document recognition" Proceedings of the IEEE, v. 86, pp. 2278- 2324, 1998.
Learning the K in K-Means - Hamerly, Elkan (2003) (4 citations) (Correct)
No context found.
Yann LeCun, L eon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.
Probability Estimates for Multi-class Classification by.. - Wu, Lin, Weng (2003) (7 citations) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, November 1998. MNIST database available at http://yann.lecun.com/exdb/mnist/.
Analyses and Tests of Handwritten - Vid Tekniska Ogskolan (Correct)
No context found.
Yann LeCun, Leon Bottou, Yoshua Bengio, and Patrick Ha ner. Gradientbased learning applied to document reconition. IEEE, November 1998. 69
S E A R C H P O R T I D I A P D a l l e M o l l e I n s t i t u t .. - Pe Cep Ua (2002) (Correct)
No context found.
Y. LeCun, L. Bottou, Y. Bengio, and P. Ha ner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, November 1998.
Learning Montages of Transformed Latent - Images As Representations (Correct)
No context found.
Y. Bengio Y. LeCun, L. Bottou and P. Ha ner, \Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, November 1998.
First 50 documents Next 50
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC