Yann LeCun

Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs

2016 · arXiv (Cornell University)

Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well as to enable ANNs to learn long-term correlations in the data. This …

Very Deep Convolutional Networks for Text Classification

2017

The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the deep convolutional networks which have pushed the …

Decoupled Contrastive Learning

2021 · arXiv (Cornell University)

Contrastive learning (CL) is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented "views" of the same image as positive to be pulled closer, and all …

Character-level Convolutional Networks for Text Classification

2015 · arXiv (Cornell University)

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons …

Very Deep Convolutional Networks for Natural Language Processing.

2016 · arXiv (Cornell University)

The dominant approach for many NLP tasks are recurrent neural networks, in particular LSTMs, and convolutional neural networks. However, these architectures are rather shallow in comparison to the deep convolutional networks which are very successful …

Tracking the World State with Recurrent Entity Networks

2016 · arXiv (Cornell University)

We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it …