Skip to search formSkip to main contentSkip to account menu

mixup: Beyond Empirical Risk Minimization

This work proposes mixup, a simple learning principle that trains a neural network on convex combinations of pairs of examples and their labels, which improves the generalization of state-of-the-art neural network architectures.
View PDF on arXiv (opens in a new tab)

Convolutional Sequence to Sequence Learning

This work introduces an architecture based entirely on convolutional neural networks, which outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT-French translation at an order of magnitude faster speed, both on GPU and CPU.
View PDF on arXiv (opens in a new tab)

Language Modeling with Gated Convolutional Networks

A finite context approach through stacked convolutions, which can be more efficient since they allow parallelization over sequential tokens, is developed and is the first time a non-recurrent approach is competitive with strong recurrent models on these large scale language tasks.
View PDF on arXiv (opens in a new tab)

Hierarchical Neural Story Generation

This work collects a large dataset of 300K human-written stories paired with writing prompts from an online forum that enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text.
View on ACL (opens in a new tab)

Theano: A Python framework for fast computation of mathematical expressions

The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
View PDF on arXiv (opens in a new tab)

Pay Less Attention with Lightweight and Dynamic Convolutions

It is shown that a very lightweight convolution can perform competitively to the best reported self-attention results, and dynamic convolutions are introduced which are simpler and more efficient than self-ATTention.
View PDF on arXiv (opens in a new tab)

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

This paper proposes a new approach to second-order optimization, the saddle-free Newton method, that can rapidly escape high dimensional saddle points, unlike gradient descent and quasi-Newton methods, and applies this algorithm to deep or recurrent neural network training, and provides numerical evidence for its superior optimization performance.
View PDF on arXiv (opens in a new tab)

Parseval Networks: Improving Robustness to Adversarial Examples

It is shown that Parseval networks match the state-of-the-art in terms of accuracy on CIFAR-10/100 and Street View House Numbers while being more robust than their vanilla counterpart against adversarial examples.
View PDF on arXiv (opens in a new tab)

Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding

This paper implemented and compared several important RNN architectures, including Elman, Jordan, and hybrid variants, and implemented these networks with the publicly available Theano neural network toolkit and completed experiments on the well-known airline travel information system (ATIS) benchmark.
View on ACM (opens in a new tab)

Deal or No Deal? End-to-End Learning of Negotiation Dialogues

For the first time, it is shown it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states, and this technique dramatically improves performance.
View on ACL (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)