Convolutional networks for images, speech, and time series

By Yann LeCun, Yoshua Bengio. 1998

Subfields: Computer Vision and Pattern Recognition, Model Architectures

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 Model Architectures

Citations in the corpus

Convolutional Sequence to Sequence Learning (2017, background): “Convolutional neural networks are less common for sequence modeling, despite several advantages (Waibel et al., 1989; LeCun & Bengio, 1995).”
Pylearn2: a machine learning research library (2013, methodology): “This includes autoencoders[6], RBMs [47] including RBMs with Gaussian visible units [54], DBMs [45], MLPs [44], convolutional networks [33], and local coordinate coding [56].”
A Deep Relevance Matching Model for Ad-hoc Retrieval (2016, methodology): “Such a matching problem formalization is often considered general in the sense that it can cover both ad-hoc retrieval tasks as well as many NLP tasks such as paraphrase identiﬁcation, question answering (QA), and automatic conversation [17, 11].”
Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015, methodology): “Convolutional neural networks Convolutional neural networks have been used to model images, speech, and time series [14].”
Learning to Extract Coherent Summary via Deep Reinforcement Learning (2018, background): “Following layer 2, there are more convolution and max-pooling layers, analogous to that of convolutional architecture for image input (LeCun and Bengio 1995).”
The jamming transition as a paradigm to understand the loss landscape of deep neural networks (2018, background): “[6] Yann LeCun, Yoshua Bengio, et al.”
Language Modeling with Gated Convolutional Networks (2016, background): “Convolu-tional networks can be stacked to represent large context sizes and extract hierarchical features over larger and larger contexts with more abstractive features (LeCun & Bengio, 1995).”
Deformable Convolutional Networks (2017, background): “Recently, convolutional neural networks (CNNs) [35] have achieved signiﬁcant success for visual recognition tasks, such as image classiﬁcation [31], semantic segmentation [41], and object detection [16].”
Wav2Letter: an End-to-End ConvNet-based Speech Recognition System (2016, methodology): “Our speech recognition system is a standard convolutional neural network [12] fed with various different features, trained through an alternative to the Connectionist Temporal Classification (CTC) [6], and coupled with a simple beam search decoder.”
Deep Convolutional Inverse Graphics Network (2015, methodology): “Models such as Convolutional Neural Networks (CNNs) [16, 13], Restricted Boltzmann Machines (RBM) based generative models [9, 25, 17], and Auto-encoders [1, 29, 20] have been successfully applied to produce multiple layers of increasingly abstract visual representations.”
Weight Agnostic Neural Networks (2019, background): “Convolutional networks [24, 56] are especially suited for image processing [16].”
Real-Time Federated Evolutionary Neural Architecture Search (2020, methodology): “The search space in NAS depends on the neural network model in use and in this work, we limit our discussions to convolutional neural networks (CNNs) [25], [26].”