Trending Research

Language Models are Unsupervised Multitask Learners

Preprint 2019 openai/gpt-2

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.

COMMON SENSE REASONING DOCUMENT SUMMARIZATION LANGUAGE MODELLING MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION

1,799
15.42 stars / hour

A Style-Based Generator Architecture for Generative Adversarial Networks

12 Dec 2018NVlabs/stylegan

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.

IMAGE GENERATION

2,928
5.03 stars / hour

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

12 Feb 2019pytorch/ELF

The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy.

GAME OF GO

2,617
1.03 stars / hour

nlp-tutorial

11 Oct 2018graykode/nlp-tutorial

Natural Language Processing Tutorial for Deep Learning Researchers

COMMON SENSE REASONING CROSS-LINGUAL NATURAL LANGUAGE INFERENCE NAMED ENTITY RECOGNITION QUESTION ANSWERING

1,472
0.89 stars / hour

Deep Neural Networks with Box Convolutions

NeurIPS 2018 shrubb/box-convolutions

Box filters computed using integral images have been part of the computer vision toolset for a long time.

SEMANTIC SEGMENTATION

68
0.86 stars / hour

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations

29 Nov 2018google-research/disentanglement_lib

On the negative side, we observe in our study that well-disentangled models seemingly cannot be identified without access to ground-truth labels even if we are allowed to transfer hyperparameters across data sets.

80
0.69 stars / hour

Bag of Tricks for Image Classification with Convolutional Neural Networks

4 Dec 2018dmlc/gluon-cv

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.

IMAGE CLASSIFICATION OBJECT DETECTION SEMANTIC SEGMENTATION TRANSFER LEARNING

1,836
0.47 stars / hour

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

ICLR 2019 huggingface/pytorch-pretrained-BERT

Transformer networks have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling.

LANGUAGE MODELLING

3,513
0.45 stars / hour

Efficient softmax approximation for GPUs

ICML 2017 huggingface/pytorch-pretrained-BERT

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies.

3,513
0.45 stars / hour