A trainable feature extractor for handwritten digit recognition

335 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Beyond spatial pyramids: Receptive field learning for pooled image features (2012, neutral): “[20] 0.”
Remaining Useful Life Prediction Based on a Double-Convolutional Neural Network Architecture (2019, background): “CNN is a special feed-forward neural network that can extract topological properties from the inputs [24].”
Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes (2007, methodology): “Greedily pretrained DBN’s can also be used to provide input vectors for other kernel-based methods, including SVMs [17, 8] and kernel regression [1], and our future research will concentrate on comparing our method to other kernel-based semi-supervised learning algorithms [4, 19].”
Deep, Big, Simple Neural Nets for Handwritten Digit Recognition (2010, background): “…trend went towards more and more complex variants of Support Vector Machines or SVMs (Decoste & Scholkopf, 2002) and combinations of NNs and SVMs (Lauer et al., 2007) etc. Convolutional neural networks (CNNs) achieved a record-breaking 0.40% error rate (Simard et al., 2003), using novel elastic…”