Object Recognition with Gradient-Based Learning

By Yann LeCun, Patrick Haffner, L. Eon Bottou, Yoshua Bengio. 1999

Subfields: Computer Vision and Pattern Recognition, Statistical Learning Theory

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Statistical Learning Theory

Citations in the corpus

Generative Adversarial Networks (2021, neutral): “GANs have various applications in different fields, including computer vision, NLP, and healthcare.”
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021, background): “Its complexity is still quadratic to image size, while ours is linear and also operates locally which has proven beneficial in modeling the high correlation in visual signals [32, 22, 37].”
Evidential Deep Learning to Quantify Classification Uncertainty (2018, methodology): “Commonly to many standardized architectures, LeNet estimates classification probabilities with the softmax function.”
CvT: Introducing Convolutions to Vision Transformers (2021, methodology): “…(convolution) convolution yes Table 1: Representative works of vision Transformers. tecture forces the capture of this local structure by using local receptive ﬁelds, shared weights, and spatial subsampling [20], and thus also achieves some degree of shift, scale, and distortion invariance.”
Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation (2019, neutral): “…& Schmidhuber, 1997) or Gated Recurrent Unit (GRU) (Cho et al., 2014)), skip connections (He et al., 2016; Huang et al., 2016), (self-)attention (Bahdanau et al., 2014; Vaswani et al., 2017), convolution (LeCun et al., 1998; 1999), and/or batch normalization (batchnorm) (Ioffe & Szegedy, 2015).”
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks (2015, methodology): “MNIST The MNIST dataset [LeCun et al., 1999] consists of 70,000 handwritten digits from 0 to 9, centered on a 28 × 28 square canvas.”
Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes (2019, background): “[36] Yann LeCun, Patrick Haffner, Léon Bottou, and Yoshua Bengio.”
Tensor Programs II: Neural Tangent Kernel for Any Architecture (2020, background): “, Long-Short Term Memory (LSTM) [33] or Gated Recurrent Unit (GRU) [14]), skip connections [31, 35], convolutions [22, 23, 42, 43, 57] or graph convolutions [11, 17, 20, 32, 40, 46], pooling [42, 43], batch normalization [38], layer normalization [8] and/or attention [9, 59].”
Automatic and Reliable Leaf Disease Detection Using Deep Learning Techniques (2021, background): “Convolutional neural network (CNN) is a very popular neural network architecture that is used successfully for a variety of computer vision tasks in diverse ﬁelds [14].”
Privacy-Preserving Classification on Deep Neural Network (2017, background): “Neural networks aim to solve a so-called classification problem which consists in correctly assigning a label to a new observation, on the basis of a training set of data containing observations (or instances) whose labelling is known [31].”
Soft-Label Dataset Distillation and Text Dataset Distillation (2019, methodology): “For example, we show that Text Dataset Distillation (TDD) can train a custom convolutional neural network (CNN) [6] with known initialization up to 90% of its original accuracy on the IMDB sentiment classification task [7] using just two synthetic sentences.”
The Manifold Tangent Classifier (2011, background): “Table 3 shows our results on the full MNIST dataset with some results taken from (LeCun et al., 1999; Hinton et al., 2006).”
M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (2019, background): “Traditionally, convolutional operations are preferred to be spatiallyinvariant [18, 19] in order to detect objects at arbitrary image locations.”
Pre-Defined Sparsity for Low-Complexity Convolutional Neural Networks (2020, unknown): “Because the SFCC [36], shown in Fig.”
Learning to detect objects in images via a sparse, part-based representation (2004, methodology): “On the learning side, methods for classifying the feature space have ranged from simple nearest-neighbor schemes to more complex approaches such as neural networks [8], convolutional neural networks [17], probabilistic methods [11], [18], and linear or higher degree polynomial classifiers [13], [16]”