Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control

19 Oct 2020combra-lab/pop-spiking-deep-rl

Here, we propose a population-coded spiking actor network (PopSAN) trained in conjunction with a deep critic network using deep reinforcement learning (DRL).

CONTINUOUS CONTROL OPENAI GYM

0
19 Oct 2020

PySBD: Pragmatic Sentence Boundary Disambiguation

19 Oct 2020nipunsadvilkar/pySBD

In this paper, we present a rule-based sentence boundary disambiguation Python package that works out-of-the-box for 22 languages.

179
19 Oct 2020

Probabilistic Linear Solvers for Machine Learning

19 Oct 2020JonathanWenger/probabilistic-linear-solvers-for-ml

Linear systems are the bedrock of virtually all numerical computation.

2
19 Oct 2020

The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification

19 Oct 2020boun-tabi/RELX

Relation classification is one of the key topics in information extraction, which can be used to construct knowledge bases or to provide useful information for question answering.

2
19 Oct 2020

A combined full-reference image quality assessment method based on convolutional activation maps

19 Oct 2020Skythianos/FRIQA-ActMapFeat

In this study, we explore a novel, combined approach which predicts the perceptual quality of a distorted image by compiling a feature vector from convolutional activation maps.

IMAGE QUALITY ASSESSMENT

0
19 Oct 2020

MaskNet: A Fully-Convolutional Network to Estimate Inlier Points

19 Oct 2020vinits5/masknet

We demonstrate these improvements on synthetic and real-world datasets.

POINT CLOUD REGISTRATION

0
19 Oct 2020

Detecting Hands and Recognizing Physical Contact in the Wild

19 Oct 2020cvlab-stonybrook/ContactHands

The first attention mechanism is based on the hand and a region's affinity, enclosing the hand and the object, and densely pools features from this region to the hand region.

3
19 Oct 2020

Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders

19 Oct 2020sisl/EvidentialSparsification

Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation.

IMAGE GENERATION MOTION PLANNING NATURAL LANGUAGE UNDERSTANDING

0
19 Oct 2020

GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation

19 Oct 2020xzwthu/GASNet

Segmentation of infected areas in chest CT volumes is of great significance for further diagnosis and treatment of COVID-19 patients.

LESION SEGMENTATION SEMANTIC SEGMENTATION ADVERSARIAL TRAINING

4
19 Oct 2020