Sinkhorn Divergence of Topological Signature Estimates for Time Series Classification

14 Feb 2019colinstephen/icmla2018

Distinguishing between classes of time series sampled from dynamic systems is a common challenge in systems and control engineering, for example in the context of health monitoring, fault detection, and quality control.

FAULT DETECTION TIME SERIES TIME SERIES CLASSIFICATION

3
14 Feb 2019

Learn a Prior for RHEA for Better Online Planning

14 Feb 2019for-xintong/p-RHEA

In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network.

0
14 Feb 2019

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

2,201
14 Feb 2019

ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning

13 Feb 2019HDI-Project/ATMSeer

To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts.

4
13 Feb 2019

Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection

13 Feb 2019dnguyengithub/AudioNovelty

In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection.

1
13 Feb 2019

3D Face Modeling from Diverse Raw Scan Data

13 Feb 2019liuf1990/3DFC

Traditional 3D models learn a latent representation of faces using linear subspaces from no more than 300 training scans of a single database.

3D FACE RECONSTRUCTION

15
13 Feb 2019

Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps

13 Feb 20191202kbs/Rectified-Gradient

Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions.

7
13 Feb 2019

SECTOR: A Neural Model for Coherent Topic Segmentation and Classification

13 Feb 2019sebastianarnold/WikiSection

From our extensive evaluation of 20 architectures, we report a highest score of 71.6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR LSTM model with bloom filter embeddings and bidirectional segmentation.

READING COMPREHENSION

0
13 Feb 2019

Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications

12 Feb 2019SymbioticLab/Salus

We show that these primitives can then be used to implement flexible sharing policies such as fairness, prioritization, and packing for various use cases.

2
12 Feb 2019

Contrastive Variational Autoencoder Enhances Salient Features

12 Feb 2019abidlabs/contrastive_vae

The cVAE explicitly models latent features that are shared between the datasets, as well as those that are enriched in one dataset relative to the other, which allows the algorithm to isolate and enhance the salient latent features.

0
12 Feb 2019