Top 10 Arxiv Papers Today
2.401 Mikeys
#1. Blameworthiness in Security Games
Pavel Naumov, Jia Tao
Security games are an example of a successful real-world application of game
theory. The paper defines blameworthiness of the defender and the attacker in
security games using the principle of alternative possibilities and provides a
sound and complete logical system for reasoning about blameworthiness in such
games. Two of the axioms of this system capture the asymmetry of information in
security games.
more |
pdf
| html
Figures
None.
Tweets
Nicochan33:
Blameworthiness in Security Games #ArtificialIntelligence #Blameworthiness #ai https://t.co/PGv1XF6v2o
amruthasuri:
Blameworthiness in Security Games #ArtificialIntelligence #Blameworthiness #ai via https://t.co/gydENhzRSg https://t.co/ZVmcjPFHDr
arxivml:
"Blameworthiness in Security Games",
Pavel Naumov, Jia Tao
https://t.co/LxBuT0y2sA
Aijobs_com:
Blameworthiness in Security Games #ArtificialIntelligence #Blameworthiness #ai https://t.co/GoFfKANSeZ
DO:
Blameworthiness in Security Games. https://t.co/DK005KxXG9
edrc30:
RT @Nicochan33: Blameworthiness in Security Games #ArtificialIntelligence #Blameworthiness #ai https://t.co/PGv1XF6v2o
AIBizDir:
RT @Nicochan33: Blameworthiness in Security Games #ArtificialIntelligence #Blameworthiness #ai https://t.co/PGv1XF6v2o
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 2
Total Words: 0
Unqiue Words: 0
2.394 Mikeys
#2. Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer
Rae Jeong, Jackie Kay, Francesco Romano, Thomas Lampe, Tom Rothorl, Abbas Abdolmaleki, Tom Erez, Yuval Tassa, Francesco Nori
Learning robotic control policies in the real world gives rise to challenges
in data efficiency, safety, and controlling the initial condition of the
system. On the other hand, simulations are a useful alternative as they provide
an abundant source of data without the restrictions of the real world.
Unfortunately, simulations often fail to accurately model complex real-world
phenomena. Traditional system identification techniques are limited in
expressiveness by the analytical model parameters, and usually are not
sufficient to capture such phenomena. In this paper we propose a general
framework for improving the analytical model by optimizing state dependent
generalized forces. State dependent generalized forces are expressive enough to
model constraints in the equations of motion, while maintaining a clear
physical meaning and intuition. We use reinforcement learning to efficiently
optimize the mapping from states to generalized forces over a discounted
infinite horizon. We show that using only minutes of real world data...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer. Rae Jeong, Jackie Kay, Francesco Romano, Thomas Lampe, Tom Rothorl, Abbas Abdolmaleki, Tom Erez, Yuval Tassa, and Francesco Nori https://t.co/N5lxmWHIqR
roadrunning01:
Modelling Generalized Forces with Reinforcement Learning
for Sim-to-Real Transfer
pdf: https://t.co/RaHrtn7G2l
abs: https://t.co/kbUBYpT8rt
https://t.co/yDa6LfsjYl
sim2realAIorg:
Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer https://t.co/Gyhbn67MCU https://t.co/sf9X1AmiiF
arxiv_cs_LG:
Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer. Rae Jeong, Jackie Kay, Francesco Romano, Thomas Lampe, Tom Rothorl, Abbas Abdolmaleki, Tom Erez, Yuval Tassa, and Francesco Nori https://t.co/uAAiq8ffLZ
syoyo:
RT @roadrunning01: Modelling Generalized Forces with Reinforcement Learning
for Sim-to-Real Transfer
pdf: https://t.co/RaHrtn7G2l
abs: http…
EricSchles:
RT @roadrunning01: Modelling Generalized Forces with Reinforcement Learning
for Sim-to-Real Transfer
pdf: https://t.co/RaHrtn7G2l
abs: http…
heghbalz:
RT @roadrunning01: Modelling Generalized Forces with Reinforcement Learning
for Sim-to-Real Transfer
pdf: https://t.co/RaHrtn7G2l
abs: http…
dave_co_dev:
RT @sim2realAIorg: Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer https://t.co/Gyhbn67MCU https://t.co/s…
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 9
Total Words: 0
Unqiue Words: 0
2.311 Mikeys
#3. Dealing with Sparse Rewards in Reinforcement Learning
Joshua Hare
Successfully navigating a complex environment to obtain a desired outcome is
a difficult task, that up to recently was believed to be capable only by
humans. This perception has been broken down over time, especially with the
introduction of deep reinforcement learning, which has greatly increased the
difficulty of tasks that can be automated. However, for traditional
reinforcement learning agents this requires an environment to be able to
provide frequent extrinsic rewards, which are not known or accessible for many
real-world environments. This project aims to explore and contrast existing
reinforcement learning solutions that circumnavigate the difficulties of an
environment that provide sparse rewards. Different reinforcement solutions will
be implemented over a several video game environments with varying difficulty
and varying frequency of rewards, as to properly investigate the applicability
of these solutions. This project introduces a novel reinforcement learning
solution, by combining aspects of two existing state of the...
more |
pdf
| html
Figures
Tweets
arxivml:
"Dealing with Sparse Rewards in Reinforcement Learning",
Joshua Hare
https://t.co/0t9kuLZ46e
arxiv_cs_LG:
Dealing with Sparse Rewards in Reinforcement Learning. Joshua Hare https://t.co/Puy6kLsX1K
SciFi:
Dealing with Sparse Rewards in Reinforcement Learning. https://t.co/Kau1lG97OM
MACKabiVIPer42:
RT @SciFi: Dealing with Sparse Rewards in Reinforcement Learning. https://t.co/Kau1lG97OM
matthewopala:
RT @SciFi: Dealing with Sparse Rewards in Reinforcement Learning. https://t.co/Kau1lG97OM
Github
A small reinforcement learning library for my masters dissertation project
Stargazers: 0
Subscribers: 1
Subscribers: 1
Forks: 0
Open Issues: 0
Open Issues: 0
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 1
Total Words: 20815
Unqiue Words: 3840
2.31 Mikeys
#4. DwNet: Dense warp-based network for pose-guided human video generation
Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, Leonid Sigal
Generation of realistic high-resolution videos of human subjects is a
challenging and important task in computer vision. In this paper, we focus on
human motion transfer - generation of a video depicting a particular subject,
observed in a single image, performing a series of motions exemplified by an
auxiliary (driving) video. Our GAN-based architecture, DwNet, leverages dense
intermediate pose-guided representation and refinement process to warp the
required subject appearance, in the form of the texture, from a source image
into a desired pose. Temporal consistency is maintained by further conditioning
the decoding process within a GAN on the previously generated frame. In this
way a video is generated in an iterative and recurrent fashion. We illustrate
the efficacy of our approach by showing state-of-the-art quantitative and
qualitative performance on two benchmark datasets: TaiChi and Fashion Modeling.
The latter is collected by us and will be made publicly available to the
community.
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
DwNet: Dense warp-based network for pose-guided human video generation. Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, and Leonid Sigal https://t.co/tcZbk57j6I
roadrunning01:
DwNet: Dense warp-based network for pose-guided human video generation
pdf: https://t.co/CVFHoZGPTD
abs: https://t.co/VZuV5JoVX3 https://t.co/s0p7qsNmwQ
arxiv_cs_LG:
DwNet: Dense warp-based network for pose-guided human video generation. Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, and Leonid Sigal https://t.co/LeXk9XavIB
arxiv_cs_cv_pr:
DwNet: Dense warp-based network for pose-guided human video generation. Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, and Leonid Sigal https://t.co/PWmOm064Jw
heghbalz:
RT @roadrunning01: DwNet: Dense warp-based network for pose-guided human video generation
pdf: https://t.co/CVFHoZGPTD
abs: https://t.co/VZ…
hey_kishore:
RT @roadrunning01: DwNet: Dense warp-based network for pose-guided human video generation
pdf: https://t.co/CVFHoZGPTD
abs: https://t.co/VZ…
MassBassLol:
RT @roadrunning01: DwNet: Dense warp-based network for pose-guided human video generation
pdf: https://t.co/CVFHoZGPTD
abs: https://t.co/VZ…
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 4
Total Words: 0
Unqiue Words: 0
2.261 Mikeys
#5. A game method for improving the interpretability of convolution neural network
Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, Yufei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, Xinhong Hei
Real artificial intelligence always has been focused on by many machine
learning researchers, especially in the area of deep learning. However deep
neural network is hard to be understood and explained, and sometimes, even
metaphysics. The reason is, we believe that: the network is essentially a
perceptual model. Therefore, we believe that in order to complete complex
intelligent activities from simple perception, it is necessary to con-struct
another interpretable logical network to form accurate and reasonable responses
and explanations to external things. Researchers like Bolei Zhou and Quanshi
Zhang have found many explanatory rules for deep feature extraction aimed at
the feature extraction stage of convolution neural network. However, although
researchers like Marco Gori have also made great efforts to improve the
interpretability of the fully connected layers of the network, the problem is
also very difficult. This paper firstly analyzes its reason. Then a method of
constructing logical network based on the fully connected...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
A game method for improving the interpretability of convolution neural network. Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, Yufei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, and Xinhong Hei https://t.co/yhLFSXM09T
arxiv_cs_LG:
A game method for improving the interpretability of convolution neural network. Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, Yufei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, and Xinhong Hei https://t.co/rDG3EMqZWc
arxiv_cscv:
A game method for improving the interpretability of convolution neural network https://t.co/Ebqafn9A6L
arxiv_cs_cv_pr:
A game method for improving the interpretability of convolution neural network. Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, Yufei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, and Xinhong Hei https://t.co/11bKw5bkRr
disigandalf:
RT @arxiv_cscv: A game method for improving the interpretability of convolution neural network https://t.co/Ebqafn9A6L
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 10
Total Words: 0
Unqiue Words: 0
2.257 Mikeys
#6. Discovering the Compositional Structure of Vector Representations with Role Learning Networks
Paul Soulos, Tom McCoy, Tal Linzen, Paul Smolensky
Neural networks (NNs) are able to perform tasks that rely on compositional
structure even though they lack obvious mechanisms for representing this
structure. To analyze the internal representations that enable such success, we
propose ROLE, a technique that detects whether these representations implicitly
encode symbolic structure. ROLE learns to approximate the representations of a
target encoder E by learning a symbolic constituent structure and an embedding
of that structure into E's representational vector space. The constituents of
the approximating symbol structure are defined by structural positions ---
roles --- that can be filled by symbols. We show that when E is constructed to
explicitly embed a particular type of structure (string or tree), ROLE
successfully extracts the ground-truth roles defining that structure. We then
analyze a GRU seq2seq network trained to perform a more complex compositional
task (SCAN), where there is no ground truth role scheme available. For this
model, ROLE successfully discovers an...
more |
pdf
| html
Figures
None.
Tweets
tdietterich:
Intriguing new paper by Paul Soulos, Tom McCoy, Tal Linzen, Paul Smolensky explains and improves DNNs by uncovering and enforcing compositional structure. https://t.co/UmHuJO4sCR
I predict @GaryMarcus will love this.
BrundageBot:
Discovering the Compositional Structure of Vector Representations with Role Learning Networks. Paul Soulos, Tom McCoy, Tal Linzen, and Paul Smolensky https://t.co/eaR9iEr5e0
arxiv_cs_LG:
Discovering the Compositional Structure of Vector Representations with Role Learning Networks. Paul Soulos, Tom McCoy, Tal Linzen, and Paul Smolensky https://t.co/kEqn6GITiB
arxiv_cscl:
Discovering the Compositional Structure of Vector Representations with Role Learning Networks https://t.co/Jy2qmnGqoN
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 4
Total Words: 0
Unqiue Words: 0
2.256 Mikeys
#7. KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning
Tarin Clanuwat, Alex Lamb, Asanobu Kitamoto
Kuzushiji, a cursive writing style, had been used in Japan for over a
thousand years starting from the 8th century. Over 3 millions books on a
diverse array of topics, such as literature, science, mathematics and even
cooking are preserved. However, following a change to the Japanese writing
system in 1900, Kuzushiji has not been included in regular school curricula.
Therefore, most Japanese natives nowadays cannot read books written or printed
just 150 years ago. Museums and libraries have invested a great deal of effort
into creating digital copies of these historical documents as a safeguard
against fires, earthquakes and tsunamis. The result has been datasets with
hundreds of millions of photographs of historical documents which can only be
read by a small number of specially trained experts. Thus there has been a
great deal of interest in using Machine Learning to automatically recognize
these historical texts and transcribe them into modern Japanese characters.
Nevertheless, several challenges in Kuzushiji recognition have...
more |
pdf
| html
Figures
None.
Tweets
tkasasagi:
KuroNet paper is now on arxiv. There are a few things to note.
1. Both 1st and 2nd authors contributed equally.
2. The data we used is different from Kaggle dataset. I adjusted the data a lot before competition so the result can’t be directly compared.
https://t.co/xJoZH4W3aB https://t.co/Id11AaXqKR
BrundageBot:
KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning. Tarin Clanuwat, Alex Lamb, and Asanobu Kitamoto https://t.co/dSiMEQ7uIX
arxiv_cs_LG:
KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning. Tarin Clanuwat, Alex Lamb, and Asanobu Kitamoto https://t.co/ABnNa2Tetg
arxiv_cs_cv_pr:
KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning. Tarin Clanuwat, Alex Lamb, and Asanobu Kitamoto https://t.co/wqC3LPmHAe
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 3
Total Words: 0
Unqiue Words: 0
2.25 Mikeys
#8. Multi-Resolution Weak Supervision for Sequential Data
Frederic Sala, Paroma Varma, Jason Fries, Daniel Y. Fu, Shiori Sagawa, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James Priest, Christopher Ré
Since manually labeling training data is slow and expensive, recent
industrial and scientific research efforts have turned to weaker or noisier
forms of supervision sources. However, existing weak supervision approaches
fail to model multi-resolution sources for sequential data, like video, that
can assign labels to individual elements or collections of elements in a
sequence. A key challenge in weak supervision is estimating the unknown
accuracies and correlations of these sources without using labeled data.
Multi-resolution sources exacerbate this challenge due to complex correlations
and sample complexity that scales in the length of the sequence. We propose
Dugong, the first framework to model multi-resolution weak supervision sources
with complex correlations to assign probabilistic labels to training data.
Theoretically, we prove that Dugong, under mild conditions, can uniquely
recover the unobserved accuracy and correlation parameters and use parameter
sharing to improve sample complexity. Our method assigns...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
Multi-Resolution Weak Supervision for Sequential Data. Frederic Sala, Paroma Varma, Jason Fries, Daniel Y. Fu, Shiori Sagawa, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James Priest, and Christopher Ré https://t.co/f3ZCCHSyvX
evolvingstuff:
Multi-Resolution Weak Supervision for Sequential Data
"improves over traditional supervision by 16.0 F1 points and existing weak supervision approaches by 24.2 F1 points across several video and sensor classification tasks"
https://t.co/Vh0dbQUMKA https://t.co/9G6Mu0QWKY
arxiv_cs_LG:
Multi-Resolution Weak Supervision for Sequential Data. Frederic Sala, Paroma Varma, Jason Fries, Daniel Y. Fu, Shiori Sagawa, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James Priest, and Christopher Ré https://t.co/c8UIfOKLRB
arxiv_cs_cv_pr:
Multi-Resolution Weak Supervision for Sequential Data. Frederic Sala, Paroma Varma, Jason Fries, Daniel Y. Fu, Shiori Sagawa, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James Priest, and Christopher Ré https://t.co/EdwKWJXkcM
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 11
Total Words: 0
Unqiue Words: 0
2.243 Mikeys
#9. MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
Dominik Müller, Frank Kramer
The increased availability and usage of modern medical imaging induced a
strong need for automatic medical image segmentation. Still, current image
segmentation platforms do not provide the required functionalities for plain
setup of medical image segmentation pipelines. Already implemented pipelines
are commonly standalone software, optimized on a specific public data set.
Therefore, this paper introduces the open-source Python library MIScnn. The aim
of MIScnn is to provide an intuitive API allowing fast building of medical
image segmentation pipelines including data I/O, preprocessing, data
augmentation, patch-wise analysis, metrics, a library with state-of-the-art
deep learning models and model utilization like training, prediction, as well
as fully automatic evaluation (e.g. cross-validation). Similarly, high
configurability and multiple open interfaces allow full pipeline customization.
Running a cross-validation with MIScnn on the Kidney Tumor Segmentation
Challenge 2019 data set (multi-class semantic segmentation with 300...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning. Dominik Müller and Frank Kramer https://t.co/ouKQMiiBtW
arxivml:
"MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning",
Dominik …
https://t.co/DVYkQltPZG
arxiv_cs_LG:
MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning. Dominik Müller and Frank Kramer https://t.co/bs0FAcfjFs
arxiv_cs_cv_pr:
MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning. Dominik Müller and Frank Kramer https://t.co/DynhpnWhqa
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 2
Total Words: 0
Unqiue Words: 0
2.241 Mikeys
#10. On Semi-Supervised Multiple Representation Behavior Learning
Ruqian Lu, Shengluan Hou
We propose a novel paradigm of semi-supervised learning (SSL)--the
semi-supervised multiple representation behavior learning (SSMRBL). SSMRBL aims
to tackle the difficulty of learning a grammar for natural language parsing
where the data are natural language texts and the 'labels' for marking data are
parsing trees and/or grammar rule pieces. We call such 'labels' as compound
structured labels which require a hard work for training. SSMRBL is an
incremental learning process that can learn more than one representation, which
is an appropriate solution for dealing with the scarce of labeled training data
in the age of big data and with the heavy workload of learning compound
structured labels. We also present a typical example of SSMRBL, regarding
behavior learning in form of a grammatical approach towards domain-based
multiple text summarization (DBMTS). DBMTS works under the framework of
rhetorical structure theory (RST). SSMRBL includes two representations: text
embedding (for representing information contained in the texts) and...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
On Semi-Supervised Multiple Representation Behavior Learning. Ruqian Lu and Shengluan Hou https://t.co/Uvb7s913TM
arxivml:
"On Semi-Supervised Multiple Representation Behavior Learning",
Ruqian Lu, Shengluan Hou
https://t.co/AeHlIewpuv
SciFi:
On Semi-Supervised Multiple Representation Behavior Learning. https://t.co/l9AKGMhWGM
arxiv_cscl:
On Semi-Supervised Multiple Representation Behavior Learning https://t.co/wBQRxHS9g1
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 2
Total Words: 0
Unqiue Words: 0
About
Assert is a website where the best academic papers on arXiv (computer science, math, physics), bioRxiv (biology), BITSS (reproducibility), EarthArXiv (earth science), engrXiv (engineering), LawArXiv (law), PsyArXiv (psychology), SocArXiv (social science), and SportRxiv (sport research) bubble to the top each day.
Papers are scored (in real-time) based on how verifiable they are (as determined by their Github repos) and how interesting they are (based on Twitter).
To see top papers, follow us on twitter @assertpub_ (arXiv), @assert_pub (bioRxiv), and @assertpub_dev (everything else).
To see beautiful figures extracted from papers, follow us on Instagram.
Tracking 210,118 papers.
Search
Sort results based on if they are interesting or reproducible.
Interesting
Reproducible