Skip to search formSkip to main contentSkip to account menu

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.
View on IEEE (opens in a new tab)

Word Translation Without Parallel Data

It is shown that a bilingual dictionary can be built between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way.
View PDF on arXiv (opens in a new tab)

Large Scale Distributed Deep Networks

This paper considers the problem of training a deep network with billions of parameters using tens of thousands of CPU cores and develops two algorithms for large-scale distributed training, Downpour SGD and Sandblaster L-BFGS, which increase the scale and speed of deep network training.
View Paper (opens in a new tab)

Gradient Episodic Memory for Continual Learning

A model for continual learning, called Gradient Episodic Memory (GEM) is proposed that alleviates forgetting, while allowing beneficial transfer of knowledge to previous tasks.
View PDF on arXiv (opens in a new tab)

DeViSE: A Deep Visual-Semantic Embedding Model

This paper presents a new deep visual-semantic embedding model trained to identify visual objects using both labeled image data as well as semantic information gleaned from unannotated text and shows that the semantic information can be exploited to make predictions about tens of thousands of image labels not observed during training.
View Paper (opens in a new tab)

Sequence Level Training with Recurrent Neural Networks

This work proposes a novel sequence level training algorithm that directly optimizes the metric used at test time, such as BLEU or ROUGE, and outperforms several strong baselines for greedy generation.
View PDF on arXiv (opens in a new tab)

Efficient Lifelong Learning with A-GEM

An improved version of GEM is proposed, dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC and other regularization-based methods.
View PDF on arXiv (opens in a new tab)

Unsupervised Machine Translation Using Monolingual Corpora Only

This work proposes a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space and effectively learns to translate without using any labeled data.
View PDF on arXiv (opens in a new tab)

What is the best multi-stage architecture for object recognition?

It is shown that using non-linearities that include rectification and local contrast normalization is the single most important ingredient for good accuracy on object recognition benchmarks and that two stages of feature extraction yield better accuracy than one.
View on IEEE (opens in a new tab)

Phrase-Based & Neural Unsupervised Machine Translation

This work investigates how to learn to translate when having access to only large monolingual corpora in each language, and proposes two model variants, a neural and a phrase-based model, which are significantly better than methods from the literature, while being simpler and having fewer hyper-parameters.
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)