NeurIPS 2015

Semi-supervised Sequence Learning

NeurIPS 2015 tensorflow/models

In our experiments, we find that long short term memory recurrent networks after being pretrained with the two approaches are more stable and generalize better.

LANGUAGE MODELLING TEXT CLASSIFICATION

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

NeurIPS 2015 facebookresearch/detectron

In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.

REAL-TIME OBJECT DETECTION

Teaching Machines to Read and Comprehend

NeurIPS 2015 facebookresearch/ParlAI

Teaching machines to read natural language documents remains an elusive challenge.

READING COMPREHENSION

BinaryConnect: Training Deep Neural Networks with binary weights during propagations

NeurIPS 2015 tensorpack/tensorpack

We introduce BinaryConnect, a method which consists in training a DNN with binary weights during the forward and backward propagations, while retaining precision of the stored weights in which gradients are accumulated.

Spatial Transformer Networks

NeurIPS 2015 tensorpack/tensorpack

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner.

Efficient and Robust Automated Machine Learning

NeurIPS 2015 automl/auto-sklearn

The success of machine learning in a broad range of applications has led to an ever-growing demand for machine learning systems that can be used off the shelf by non-experts.

HYPERPARAMETER OPTIMIZATION

Learning to Segment Object Candidates

NeurIPS 2015 facebookresearch/deepmask

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier.

OBJECT DETECTION

Character-level Convolutional Networks for Text Classification

NeurIPS 2015 gaussic/text-classification-cnn-rnn

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification.

SENTIMENT ANALYSIS TEXT CLASSIFICATION

Pointer Networks

NeurIPS 2015 PaddlePaddle/models

It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the input sequence as the output.

COMBINATORIAL OPTIMIZATION

Skip-Thought Vectors

NeurIPS 2015 ryankiros/skip-thoughts

The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice.