Top 10 Arxiv Papers Today
2.163 Mikeys
#1. Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
Mike Innes, Alan Edelman, Keno Fischer, Chris Rackauckus, Elliot Saba, Viral B Shah, Will Tebbutt
Scientific computing is increasingly incorporating the advancements in
machine learning and the ability to work with large amounts of data. At the
same time, machine learning models are becoming increasingly sophisticated and
exhibit many features often seen in scientific computing, stressing the
capabilities of machine learning frameworks. Just as the disciplines of
scientific computing and machine learning have shared common underlying
infrastructure in the form of numerical linear algebra, we now have the
opportunity to further share new computational infrastructure, and thus ideas,
in the form of Differentiable Programming. We describe Zygote, a Differentiable
Programming system that is able to take gradients of general program
structures. We implement this system in the Julia programming language. Our
system supports almost all language constructs (control flow, recursion,
mutation, etc.) and compiles high-performance code without requiring any user
intervention or refactoring to stage computations. This enables an...
more |
pdf
| html
Figures
Tweets
hackernewsbot:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/7Qts4wrsdo
newsycombinator:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/KaxnXxhykm
HNTweets:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing: https://t.co/zao7Ap1HxC Comments: https://t.co/lJVoWcGWmt
octonion:
A Differentiable Programming System to Bridge ML and Scientific Computing - https://t.co/OPZZIWwz6J
michael_nielsen:
I hope this is part of a trend exploring more and more in this direction. As @karpathy said, "gradient descent is a better programmer than you": https://t.co/2t1Sp0YOcz https://t.co/FhxtH9YUe2
newsycombinator:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/KaxnXxhykm
newsyc250:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/ylVaDjURgn (https://t.co/OLEttM3vd1)
BrundageBot:
Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing. Mike Innes, Alan Edelman, Keno Fischer, Chris Rackauckus, Elliot Saba, Viral B Shah, and Will Tebbutt https://t.co/l1fve59SfR
lobsters:
A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
via @as1ndu
https://t.co/LBzkVlVerL #ai #compsci
https://t.co/zuyuD5NM14
ireneista:
Holy shit. The machines are coming for our job.
(Okay, not *quite*. But on first read, it seems like a huge step. We didn't previously know that the field of differentiable programming existed.)
https://t.co/niS0Tcm6sg
newsyc200:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/YGIEXeJDbt (https://t.co/wMBSByZ7kW)
jreuben1:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/m38DjLbpJk
ChrisRackauckas:
#julialang is enabling scientific machine learning. Take at a the paper submitted to NeurIPS, which showcases quantum machine learning and neural stochastic differential equation (neural SDE) as applications. Many talks at #juliacon will explore this idea
https://t.co/HjzCqXOEOu
hn_frontpage:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing
L: https://t.co/bykofKZqX0
C: https://t.co/9FDYOgQGW9
watrcoolr:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/p7HItrbw47
brendanjmeade:
I want to believe (in @JuliaLanguage): https://t.co/NgcTqaxXdR
M157q_News_RSS:
A Differentiable Programming System to Bridge ML and Scientific Computing
https://t.co/Dk30roQxJG
Article URL: https://t.co/Dk30roQxJG Comments URL: https://t.co/Xsr95w3WGO Points: 113 # Comments: 12
M157q_News_RSS:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing
https://t.co/Dk30roQxJG
Article URL: https://t.co/Dk30roQxJG Comments URL: https://t.co/Xsr95w3WGO Points: 100 # Comments: 10
RebelDevNews:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/70ebxpWGeD
hackernewsj:
∂P：MLと科学計算を橋渡しする微分可能プログラミングシステム https://t.co/TwhgCIXItt
SimonDanisch:
If I hooked anyone with my @curry_on_conf talk (https://t.co/P0uJrLwve6) here is a great further read: https://t.co/cHdjksPQ3S It explains all the interesting bits I couldn't dive into! (How ML, Scientific Computing and AD all come together in #JuliaLang )
hackernewsfeed:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/tYeelWKbj2
arxivml:
"Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing",
Mike Innes, Alan…
https://t.co/we9bBx8HCO
stephenrra:
Zygote: A system for ∂P capabilities in Julia: https://t.co/qi7jPGQxeO
hackernews100:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/9dfijLKTxf
jargnar:
This was such a wonderful read! "A differentiable programming system to bridge machine learning and scientific computing" https://t.co/1YgR0Ud9Nr
osibot:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/2zJDwMzVZc
tmcpro:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/T17ksJ7Y2t
emsal1863:
https://t.co/7ist4tTvtD
"∂P: A Differentiable Programming System to Bridge ML and Scientific Computing"
This is some exciting stuff. The lstm example in sec 3.1 is crazy
hacker_news_hir:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing : https://t.co/HdFbUL8XT5 Comments: https://t.co/okBaDf6dQe
HighSNHN:
A Differentiable Programming System to Bridge ML and Scientific Computing: https://t.co/bvNgxqHFCy ( https://t.co/GgCdjirtlw )
hackernewsrobot:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/EObtu6cTs2
hereticreader:
Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing - https://t.co/9D1COPFWPY https://t.co/Z7bgDp7jTr
betterhn100:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/o13787ZX5i
TheNisargDave:
Worth reading: A differentiable programming system for modern machine learning and scientific computing applications,
https://t.co/O5LwH1IQVg
rogerluorl18:
Zygote paper is out with a VQE demo made with Yao! I'm looking forward to the talk. Nice work @MikeJInnes
https://t.co/ruSQkk2CJN
_mangesh_tekale:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/dCyoKw0Ao9
_mangesh_tekale:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/dCyoKw0Ao9
arxiv_cs_LG:
Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing. Mike Innes, Alan Edelman, Keno Fischer, Chris Rackauckus, Elliot Saba, Viral B Shah, and Will Tebbutt https://t.co/SyfNUr58eT
mohapsat:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/gj3VM18ts9 #AI #news #tech
e3pi:
#ml #DeepLearning #julialang #c01e
"..Zygote -a differentiable programming system that is able to take gradients of general program..in the Julia
https://t.co/qmBKBY0zts https://t.co/qWgJiukH1O
deeplearning4j:
A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
https://t.co/qElMO1Ks8M
betterhn50:
54 – ∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/kHiOmeQ7iO
gfrphy:
so Zygote paper has been published. I'm too excited with this ^^
https://t.co/ROWdcQ5yjJ
Zygote is one of the most ambitious Julia Project after JuMP project.
Memoirs:
Zygote: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing. https://t.co/GyE0DKQC1w
Hn150:
A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/3CuWqDbraF (https://t.co/YTOf3XPRGk)
exaday:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/Pn0h4Nfycb
wasnhierlos:
∂P: A Differentiable Programming System to Bridge ML and Scientific Computing - https://t.co/lJ0npQpmbI
aficionado:
A Differentiable Programming System to Bridge Machine Learning and Scientific Computing https://t.co/Ys9C8VqvA0
SantchiWeb:
RT @aficionado: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing https://t.co/Ys9C8VqvA0
maymounkov:
RT @newsycombinator: ∂P: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/KaxnXxhykm
hailaioverlords:
RT @mohapsat: A Differentiable Programming System to Bridge ML and Scientific Computing https://t.co/gj3VM18ts9 #AI #news #tech
en_zxteloiv:
RT @deeplearning4j: A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
https://t.co/qElMO1Ks8M
Github
Stargazers: 19
Subscribers: 5
Subscribers: 5
Forks: 6
Open Issues: 1
Open Issues: 1
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 7
Total Words: 5870
Unqiue Words: 2362
2.116 Mikeys
#2. Global AI Ethics: A Review of the Social Impacts and Ethical Implications of Artificial Intelligence
Alexa Hagerty, Igor Rubinov
The ethical implications and social impacts of artificial intelligence have
become topics of compelling interest to industry, researchers in academia, and
the public. However, current analyses of AI in a global context are biased
toward perspectives held in the U.S., and limited by a lack of research,
especially outside the U.S. and Western Europe.
This article summarizes the key findings of a literature review of recent
social science scholarship on the social impacts of AI and related technologies
in five global regions. Our team of social science researchers reviewed more
than 800 academic journal articles and monographs in over a dozen languages.
Our review of the literature suggests that AI is likely to have markedly
different social impacts depending on geographical setting. Likewise,
perceptions and understandings of AI are likely to be profoundly shaped by
local cultural and social context.
Recent research in U.S. settings demonstrates that AI-driven technologies
have a pattern of entrenching social divides and...
more |
pdf
| html
Figures
None.
Tweets
alexvespi:
Global AI Ethics: A Review of the Social Impacts and Ethical Implications of Artificial Intelligence
https://t.co/EwoA6hbUry https://t.co/ywDPFjstyx
IEthics:
@EmeryJohnR On a related note: https://t.co/YQbc6UQZAk
net_science:
Global AI Ethics: A Review of the Social Impacts and Ethical Implications of Artificial Intelligence. (arXiv:1907.07892v1 [https://t.co/umDFgVrzkA]) https://t.co/4oKNEOMFJM
baxterkb:
@anthroptimist @_TimOBrien Link to full paper!
"AI-driven technologies have a pattern of
entrenching social divides & exacerbating social inequality, particularly among historically marginalized groups. Our literature review indicates that this pattern exists on a global scale, ..."
https://t.co/gXn0UbFqrC
SanNuvola:
@sjd969 well, turns out a global distillation of the whole research project did in fact come out, so: https://t.co/qlcsERnLij
SanNuvola:
working with @Dovetail_Labs on the research project behind this report has been a rewarding experience - if you're interested in AI, ethics, and ethnographic research on global tech development, click right here: https://t.co/qlcsERnLij
SanNuvola:
@jjding99 well, nothing China-specific out in the open yet, but you might find this of interest https://t.co/qlcsERnLij
AnjaKasp:
‘Despite the need to understand how AI affects people around the world, a truly global perspective remains a critical blind spot in the ethics conversation’. Interesting AI research literature review by @anthroptimist @igRubinov: https://t.co/6oCEX7VCga https://t.co/SSrJF9ACKt
nikimari:
Ethical implications & social impacts of AI are topics of interest to industry, researchers in academia, and the public. Analyses of #AI in a global context are biased toward U.S. perspectives & limited by lack of research, especially outside the U.S.
https://t.co/Os38AgUcs2
_TimOBrien:
Today @Dovetail_Labs published a MSFT funded paper written by @anthroptimist & @igRubinov which details gaps in knowledge/understanding of #AIethics globally, steps to address it, and what regulation could mean for people in different areas of the world. https://t.co/SIz2uA0UOX
_TimOBrien:
Today @Dovetail_Labs published a MSFT-funded paper written by @Alexa & @igRubinov which details gaps in knowledge and understanding of #AIethics globally, steps to address this, and what regulation could mean for people in different areas of the world. https://t.co/SIz2uA0UOX
mikkoviitaila:
Itse artikkeli löytyy täältä: https://t.co/LN5nXVFh7s
Dovetail_Labs:
Any real discussion of AI ethics demands that we understand the impacts of these technologies on people's lives everywhere, not just in the US & EU. Our new paper takes stock of what we know & where we need to go https://t.co/y0yF7p7y92
#AIethics #datajustice
Dovetail_Labs:
Any real discussion of AI ethics means understanding the the impacts of these technologies on people's lives everywhere, not just in the US & EU. Our new paper takes stock of what we know & where we need to go https://t.co/y0yF7p7y92
#AIethics #datajustice #GlobalAI
igRubinov:
For #AI to benefit people everywhere, we must understand its effect on communities globally. Check out the results of our new paper on “AI Ethics: A Global Perspective” co-written with @anthroptimist https://t.co/ijU8EYu0RI https://t.co/RCnzh9LhfV
anthroptimist:
How do AI systems impact people's lives beyond the global North? Igor Rubinov @igRubinov and I tackle the topic in our new paper. https://t.co/GGAL4JgXqO (photo credit Martin Adams) https://t.co/XIfC2nl20u
Github
None.
Youtube
None.
Other stats
Sample Sizes : [1551634743, 1551634743]
Authors: 2
Total Words: 13195
Unqiue Words: 4860
2.102 Mikeys
#3. On the Evaluation of Conditional GANs
Terrance DeVries, Adriana Romero, Luis Pineda, Graham W. Taylor, Michal Drozdzal
Conditional Generative Adversarial Networks (cGANs) are finding increasingly
widespread use in many application domains. Despite outstanding progress,
quantitative evaluation of such models often involves multiple distinct metrics
to assess different desirable properties such as image quality,
intra-conditioning diversity, and conditional consistency, making model
benchmarking challenging. In this paper, we propose the Frechet Joint Distance
(FJD), which implicitly captures the above mentioned properties in a single
metric. FJD is defined as the Frechet Distance of the joint distribution of
images and conditionings, making it less sensitive to the often limited
per-conditioning sample size. As a result, it scales more gracefully to
stronger forms of conditioning such as pixel-wise or multi-modal conditioning.
We evaluate FJD on a modified version of the dSprite dataset as well as on the
large scale COCO-Stuff dataset, and consistently highlight its benefits when
compared to currently established metrics. Moreover, we use the...
more |
pdf
| html
Figures
None.
Tweets
DataScientistFr:
On the Evaluation of Conditional GANs
pdf: https://t.co/X003SLfAOv …
abs: https://t.co/361Zw38l0y https://t.co/bl3VtD561W - https://t.co/gHHBfXNWDs #datascience thanks @RichardEudes
udoooom:
On the Evaluation of Conditional GANs
Terrance DeVries, Adriana Romero, Luis Pineda, Graham W. Taylor, Michal Drozdzal
https://t.co/B2qHIEG7aQ
AnalyticsFr:
On the Evaluation of Conditional GANs
pdf: https://t.co/QUAhhTIL1X …
abs: https://t.co/rdfr9ng9fI https://t.co/iZGQPMgEGT - https://t.co/DCwj86Fjb0 #Analytics thanks @RichardEudes
roadrunning01:
On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
arxivml:
"On the Evaluation of Conditional GANs",
Terrance DeVries, Adriana Romero, Luis Pineda, Graham W． Taylor, Michal Dr…
https://t.co/PQHExCpehd
Memoirs:
On the Evaluation of Conditional GANs. https://t.co/D2GbCtPhTA
arxiv_cscv:
On the Evaluation of Conditional GANs https://t.co/4uC9jOWkkY
arxiv_cscv:
On the Evaluation of Conditional GANs https://t.co/4uC9jOWkkY
arxiv_cscv:
On the Evaluation of Conditional GANs https://t.co/4uC9jOWkkY
arxiv_cscv:
On the Evaluation of Conditional GANs https://t.co/4uC9jOWkkY
ceobillionaire:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
jm_alexia:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
kastnerkyle:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
ayirpelle:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
udoooom:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
heghbalz:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
hrs1985:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
cighos:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
ajnovice:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
AliceICecile:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
junsukchoe:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
iamx9000:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
Pol09122455:
RT @roadrunning01: On the Evaluation of Conditional GANs
pdf: https://t.co/TAyVnigC94
abs: https://t.co/mSKBFde4ts https://t.co/oocnOIxDGF
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 5
Total Words: 0
Unqiue Words: 0
2.099 Mikeys
#4. OmniNet: A unified architecture for multi-modal multi-task learning
Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain
Transformer is a popularly used neural network architecture, especially for
language understanding. We introduce an extended and unified architecture which
can be used for tasks involving a variety of modalities like image, text,
videos, etc. We propose a spatio-temporal cache mechanism that enables learning
spatial dimension of the input in addition to the hidden states corresponding
to the temporal input sequence. The proposed architecture further enables a
single model to support tasks with multiple input modalities as well as
asynchronous multi-task learning, thus we refer to it as OmniNet. For example,
a single instance of OmniNet can concurrently learn to perform the tasks of
part-of-speech tagging, image captioning, visual question answering and video
activity recognition. We demonstrate that training these four tasks together
results in about three times compressed model while retaining the performance
in comparison to training them individually. We also show that using this
neural network pre-trained on some modalities...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
OmniNet: A unified architecture for multi-modal multi-task learning. Subhojeet Pramanik, Priyanka Agrawal, and Aman Hussain https://t.co/ifFUyz1vDI
shunk031:
OmniNet: A unified architecture for multi-modal multi-task learning. (arXiv:1907.07804v1 [cs.LG])
https://t.co/YssxeI0lAS
arxivml:
"OmniNet: A unified architecture for multi-modal multi-task learning",
Subhojeet Pramanik, Priyanka Agrawal, Aman H…
https://t.co/IzswUnNFFM
subho406:
OmniNet is the first-ever truly universal architecture for multi-modal multi-task learning.
https://t.co/VPsnqwClTj
#ArtificialIntelligence #MachineLearning #DeepLearning #NeuralNetworks
@JeffDean @hardmaru @iamtrask @IBMResearch @Google @Microsoft https://t.co/Sv1iC42Uvg
Survive_Custom:
https://t.co/Frlkly5VWm
Progress of AGI? #ArtificialIntelligence #AGI
StatsPapers:
OmniNet: A unified architecture for multi-modal multi-task learning. https://t.co/zcqnauKYkp
arxiv_cscv:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/8DeYZMwZVP
arxiv_cscv:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/8DeYZMwZVP
arxiv_cscv:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/8DeYZMwZVP
arxiv_cscl:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/5imNbatxK9
arxiv_cscl:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/5imNbatxK9
arxiv_cscl:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/5imNbatxK9
arxiv_cscl:
OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/5imNbatxK9
TheCuriousLuke:
RT @subho406: OmniNet is the first-ever truly universal architecture for multi-modal multi-task learning.
https://t.co/VPsnqwClTj
#Artifi…
SythonUK:
RT @arxiv_cscl: OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/5imNbatxK9
sleeping_michi:
RT @arxiv_cscl: OmniNet: A unified architecture for multi-modal multi-task learning https://t.co/5imNbatxK9
SambitIllumina:
RT @subho406: OmniNet is the first-ever truly universal architecture for multi-modal multi-task learning.
https://t.co/VPsnqwClTj
#Artifi…
hrsma2i:
RT @shunk031: OmniNet: A unified architecture for multi-modal multi-task learning. (arXiv:1907.07804v1 [cs.LG])
https://t.co/YssxeI0lAS
mrityunjay_99:
RT @subho406: OmniNet is the first-ever truly universal architecture for multi-modal multi-task learning.
https://t.co/VPsnqwClTj
#Artifi…
mahesh21aug:
RT @subho406: OmniNet is the first-ever truly universal architecture for multi-modal multi-task learning.
https://t.co/VPsnqwClTj
#Artifi…
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 3
Total Words: 0
Unqiue Words: 0
2.075 Mikeys
#5. Evaluating the Utility of Document Embedding Vector Difference for Relation Learning
Jingyuan Zhang, Timothy Baldwin
Recent work has demonstrated that vector offsets obtained by subtracting
pretrained word embedding vectors can be used to predict lexical relations with
surprising accuracy. Inspired by this finding, in this paper, we extend the
idea to the document level, in generating document-level embeddings,
calculating the distance between them, and using a linear classifier to
classify the relation between the documents. In the context of duplicate
detection and dialogue act tagging tasks, we show that document-level
difference vectors have utility in assessing document-level similarity, but
perform less well in multi-relational classification.
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
Evaluating the Utility of Document Embedding Vector Difference for Relation Learning. Jingyuan Zhang and Timothy Baldwin https://t.co/wrDK0WLOFo
arxivml:
"Evaluating the Utility of Document Embedding Vector Difference for Relation Learning",
Jingyuan Zhang, Timothy Bal…
https://t.co/69KKi4Q1Tz
arxiv_cscl:
Evaluating the Utility of Document Embedding Vector Difference for Relation Learning https://t.co/YmAhGHGQVh
arxiv_cscl:
Evaluating the Utility of Document Embedding Vector Difference for Relation Learning https://t.co/YmAhGHYrMP
arxiv_cscl:
Evaluating the Utility of Document Embedding Vector Difference for Relation Learning https://t.co/YmAhGHGQVh
arxiv_cscl:
Evaluating the Utility of Document Embedding Vector Difference for Relation Learning https://t.co/YmAhGHGQVh
Github
InferSent sentence embeddings
Stargazers: 1635
Subscribers: 73
Subscribers: 73
Forks: 345
Open Issues: 19
Open Issues: 19
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 2
Total Words: 5993
Unqiue Words: 2060
2.066 Mikeys
#6. Embedding Climate Change Engagement in Astronomy Education and Research
Kathryn Williamson, Travis A. Rector, James Lowenthal
This White Paper is a call to action for astronomers to respond to climate
change with a large structural transition within our profession. Many
astronomers are deeply concerned about climate change and act upon it in their
personal and professional lives, and many organizations within astronomy have
incorporated incremental changes. We need a collective impact model to better
network and grow our efforts so that we can achieve results that are on the
scale appropriate to address climate change at the necessary level indicated by
scientific research; e.g., becoming carbon neutral by 2050. We need to
implement strategies within two primary drivers of our field: (1) Education and
Outreach, and (2) Research Practices and Infrastructure. (1) In the classroom
and through public talks, astronomers reach a large audience. Astronomy is
closely connected to the science of climate change, and it is arguably the most
important topic we include in our curriculum. Due to misinformation and
disinformation, climate change communication is...
more |
pdf
| html
Figures
Tweets
meg_bedell:
This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers can combat climate change as part of our everyday education+research practices. https://t.co/tLwzTfwFC1
rybizki:
Love that:
Embedding Climate Change Engagement in Astronomy Education and Research https://t.co/a1YvLRbNVm https://t.co/qyl3RPuvwO
KarenLMasters:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
mpoessel:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
johannateske:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
abigailStev:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
rareflwr41:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
laurawatkins_:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
nay_lynn_:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
djulik:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
marianojavierd1:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
KnudJahnke:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
plazasmalagon1:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
mshabram:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
M_N_Guenther:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
piffilicious:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
cloudfreekat:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
cesharon:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
UChadaya:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
jeppehans:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
GrilledSleazy:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
SkeptikBeliever:
RT @meg_bedell: This is a must-read white paper: https://t.co/HT4fjIDsKb -- includes excellent concrete suggestions for ways we astronomers…
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 3
Total Words: 4278
Unqiue Words: 1715
2.064 Mikeys
#7. EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
Peixiang Zhong, Di Wang, Chunyan Miao
In this paper, we propose a regularized graph neural network (RGNN) for
EEG-based emotion recognition. EEG signals measure the neuronal activities on
different brain regions via electrodes attached on them. Existing studies do
not exploit the topological structure of EEG signals effectively. Our RGNN
model is biologically supported and captures both local and global
inter-channel relations. In addition, we propose two regularizers, namely
NodeDAT and EmotionDL, to improve the robustness of our model against
cross-subject EEG variations and noisy labels during recording. To thoroughly
evaluate our model, we conduct extensive experiment in both subject-dependent
and subject-independent classification settings on two public datasets SEED and
SEED-IV. Our model obtains better performance than a few competitive baselines
such as SVM, DBN, DGCNN, BiDANN, and the state-of-the-art BiHDM on most of the
tasks. Our model analysis demonstrates that our proposed biologically-supported
adjacency matrix and two regularizers contribute consistent...
more |
pdf
| html
Figures
None.
Tweets
BrundageBot:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks. Peixiang Zhong, Di Wang, and Chunyan Miao https://t.co/XjzxnAa9nY
arxivml:
"EEG-Based Emotion Recognition Using Regularized Graph Neural Networks",
Peixiang Zhong, Di Wang, Chunyan Miao
https://t.co/ttb3Sax2lS
arxiv_cs_LG:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks. Peixiang Zhong, Di Wang, and Chunyan Miao https://t.co/TBq7kalN9W
Memoirs:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks. https://t.co/Q5vGUfgQRc
arxiv_cscv:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/4euZ6f2fvU
arxiv_cscv:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/4euZ6fjQns
arxiv_cscv:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/4euZ6f2fvU
arxiv_cscv:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/4euZ6f2fvU
arxiv_cshc:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/1DBT0AiCH8
arxiv_cshc:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/1DBT0AiCH8
arxiv_cshc:
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks https://t.co/1DBT0AiCH8
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 3
Total Words: 0
Unqiue Words: 0
2.058 Mikeys
#8. MintNet: Building Invertible Neural Networks with Masked Convolutions
Yang Song, Chenlin Meng, Stefano Ermon
We propose a new way of constructing invertible neural networks by combining
simple building blocks with a novel set of composition rules. This leads to a
rich set of invertible architectures, including those similar to ResNets.
Inversion is achieved with a locally convergent iterative procedure that is
parallelizable and very fast in practice. Additionally, the determinant of the
Jacobian can be computed analytically and efficiently, enabling their
generative use as flow models. To demonstrate their flexibility, we show that
our invertible neural networks are competitive with ResNets on MNIST and
CIFAR-10 classification. When trained as generative models, our invertible
networks achieve new state-of-the-art likelihoods on MNIST, CIFAR-10 and
ImageNet 32x32, with bits per dimension of 0.98, 3.32 and 4.06 respectively.
more |
pdf
| html
Figures
Tweets
BrundageBot:
MintNet: Building Invertible Neural Networks with Masked Convolutions. Yang Song, Chenlin Meng, and Stefano Ermon https://t.co/alTMuqf8i6
markomanka:
MintNet: Building invertible neural networks with masked convolutions
https://t.co/lGEgWfXvFJ https://t.co/k7hja5zE6a
arxivml:
"MintNet: Building Invertible Neural Networks with Masked Convolutions",
Yang Song, Chenlin Meng, Stefano Ermon
https://t.co/9amPEfb0g9
YSongStanford:
Joint work with Chenlin Meng and @ermonste. Paper link: https://t.co/TFZIUMwHfg
arxiv_cs_LG:
MintNet: Building Invertible Neural Networks with Masked Convolutions. Yang Song, Chenlin Meng, and Stefano Ermon https://t.co/2cNrhyijsc
StatsPapers:
MintNet: Building Invertible Neural Networks with Masked Convolutions. https://t.co/hn3pxQzLfm
arxiv_cscv:
MintNet: Building Invertible Neural Networks with Masked Convolutions https://t.co/Hq1xfNMz5D
arxiv_cscv:
MintNet: Building Invertible Neural Networks with Masked Convolutions https://t.co/Hq1xfNMz5D
arxiv_cscv:
MintNet: Building Invertible Neural Networks with Masked Convolutions https://t.co/Hq1xfNMz5D
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 3
Total Words: 8701
Unqiue Words: 2108
2.057 Mikeys
#9. CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation
Hongying Liu, Xiongjie Shen, Fanhua Shang, Fei Wang
This paper proposes a novel cascaded U-Net for brain tumor segmentation.
Inspired by the distinct hierarchical structure of brain tumor, we design a
cascaded deep network framework, in which the whole tumor is segmented firstly
and then the tumor internal substructures are further segmented. Considering
that the increase of the network depth brought by cascade structures leads to a
loss of accurate localization information in deeper layers, we construct many
skip connections to link features at the same resolution and transmit detailed
information from shallow layers to the deeper layers. Then we present a loss
weighted sampling (LWS) scheme to eliminate the issue of imbalanced data during
training the network. Experimental results on BraTS 2017 data show that our
architecture framework outperforms the state-of-the-art segmentation
algorithms, especially in terms of segmentation sensitivity.
more |
pdf
| html
Figures
Tweets
arxiv_org:
CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation. https://t.co/5Wx6PJcUW1 https://t.co/Nf14H2MGx4
arxivml:
"CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation",
Hongying Liu, Xiongjie Shen, Fan…
https://t.co/wczD1Z4H0f
Memoirs:
CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation. https://t.co/f7hU6slI3h
arxiv_cscv:
CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2tINAO
arxiv_cscv:
CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2tINAO
arxiv_cscv:
CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2u0osm
arxiv_cscv:
CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2tINAO
yuki_mimu:
RT @arxiv_cscv: CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2u0osm
disigandalf:
RT @arxiv_cscv: CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2u0osm
SythonUK:
RT @arxiv_cscv: CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation https://t.co/mBET2u0osm
bcmachlearn:
RT @arxiv_org: CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation. https://t.co/5Wx6PJcUW1 https://t.co/Nf14H2…
straybrid:
RT @arxiv_org: CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation. https://t.co/5Wx6PJcUW1 https://t.co/Nf14H2…
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 4
Total Words: 3298
Unqiue Words: 1261
2.056 Mikeys
#10. XFake: Explainable Fake News Detector with Visualizations
Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, Xia Hu
In this demo paper, we present the XFake system, an explainable fake news
detector that assists end-users to identify news credibility. To effectively
detect and interpret the fakeness of news items, we jointly consider both
attributes (e.g., speaker) and statements. Specifically, MIMIC, ATTN and PERT
frameworks are designed, where MIMIC is built for attribute analysis, ATTN is
for statement semantic analysis and PERT is for statement linguistic analysis.
Beyond the explanations extracted from the designed frameworks, relevant
supporting examples as well as visualization are further provided to facilitate
the interpretation. Our implemented system is demonstrated on a real-world
dataset crawled from PolitiFact, where thousands of verified political news
have been collected.
more |
pdf
| html
Figures
None.
Tweets
arxiv_org:
XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
arxivml:
"XFake: Explainable Fake News Detector with Visualizations",
Fan Yang, Shiva K． Pentyala, Sina Mohseni, Mengnan Du,…
https://t.co/0z3O5prkRh
Memoirs:
XFake: Explainable Fake News Detector with Visualizations. https://t.co/aYWoUMZb3r
arxiv_cscl:
XFake: Explainable Fake News Detector with Visualizations https://t.co/13XoWOXXNh
arxiv_cscl:
XFake: Explainable Fake News Detector with Visualizations https://t.co/13XoWOXXNh
arxiv_cscl:
XFake: Explainable Fake News Detector with Visualizations https://t.co/13XoWOXXNh
jaialkdanel:
RT @arxiv_org: XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
RexDouglass:
RT @arxiv_org: XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
RexDouglass:
RT @arxiv_cscl: XFake: Explainable Fake News Detector with Visualizations https://t.co/13XoWOXXNh
AixinSG:
RT @arxiv_org: XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
kato_kohaku:
RT @arxiv_org: XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
hengcherkeng:
RT @arxiv_org: XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
straybrid:
RT @arxiv_org: XFake: Explainable Fake News Detector with Visualizations. https://t.co/Y08bjt7cUD https://t.co/NtoQQslm4n
Github
None.
Youtube
None.
Other stats
Sample Sizes : None.
Authors: 9
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 160,434 papers.
Search
Sort results based on if they are interesting or reproducible.
Interesting
Reproducible