Tootfinder

Opt-in global Mastodon full text search. Join the index!

@drahardja@sfba.social
2024-05-14 17:45:29

Watching #GoogleIO with deep, deep skepticism. Everything shown today seem centered around #AI, and I find it very hard to trust that these products will work *in any way* like they claim they would. The long tail for all of these problem domains feel very fat and very long.

@arXiv_csCV_bot@mastoxiv.page
2024-06-14 08:59:18

This arxiv.org/abs/2406.07707 has been replaced.
initial toot: mastoxiv.page/@arXiv_csCV_…

@sauer_lauwarm@mastodon.social
2024-06-14 12:30:51

In science and scholarship, a celebration of achievements is always only a moment of pause, a moment for taking a deep breath before our work, driven by curiosity and commitment to the advancement of knowledge, continues.

@tiotasram@kolektiva.social
2024-06-12 11:40:32

Subtoot 'cause the post I saw had enough replies already, but this is a bad article (though it has a wonderful description of how Von Neumann machines work):
aeon.co/essays/your-brain-does
For context, I'm against most uses of modern LLMs for several good ethical reasons, and I think the current state of AI research funding is both unsustainable and harmful to knowledge development. However, I've done a tiny bit of deep learning research myself, and I think the tech has a lot of cool potential, even if on balance it might have even more terrifying-potential.
The central problem with this article is that while it accurately describes ways that most human brains differ fundamentally from one way computers can be set up, it completely ignores how (computer) neutral networks work, including the fact that they'd perform very similar to the humans on the dollar bill task, because they encode a representation of their training inputs as distributed tweaks to the connection weights of many simulated neurons. (Also, people with photographic memory do exist...)
I think that being challenged in one's metaphors is a great idea (read Paul Agre on AI) and this is a useful article to have read for that reason, but I think the more useful stance is a principled agnosticism towards whether the human brain works like a computer, along with a broader imagination for "what a computer works like." More specifically, I'm quite convinced the brain doesn't work like a modern operating system (effectively the central straw man in this article), but I reserve judgement on whether it works like a neutral network.

@robpike@hachyderm.io
2024-06-12 07:02:06

I was lucky enough to work in Ed Stone's cosmic ray lab when I was a graduate student. He was one of the greatest leaders I've ever known, while remaining so calm and solid and just plain deep. Principal scientist on Voyager, later head of the JPL, then the TMT and much more. An amazing, inspirational man. So sad to see him go but he had a truly great and influential life. There are few like him.

@arXiv_csSE_bot@mastoxiv.page
2024-06-13 07:22:31

What do we know about Hugging Face? A systematic literature review and quantitative validation of qualitative claims
Jason Jones, Wenxin Jiang, Nicholas Synovic, George K. Thiruvathukal, James C. Davis
arxiv.org/abs/2406.08205

@arXiv_statML_bot@mastoxiv.page
2024-06-13 09:52:25

This arxiv.org/abs/2402.03990 has been replaced.
link: scholar.google.com/scholar?q=a

@sauer_lauwarm@mastodon.social
2024-06-14 12:30:51

In science and scholarship, a celebration of achievements is always only a moment of pause, a moment for taking a deep breath before our work, driven by curiosity and commitment to the advancement of knowledge, continues.

@arXiv_csAR_bot@mastoxiv.page
2024-06-13 06:46:41

ONNXim: A Fast, Cycle-level Multi-core NPU Simulator
Hyungkyu Ham, Wonhyuk Yang, Yunseon Shin, Okkyun Woo, Guseul Heo, Sangyeop Lee, Jongse Park, Gwangsun Kim
arxiv.org/abs/2406.08051

@robpike@hachyderm.io
2024-06-12 07:02:06

I was lucky enough to work in Ed Stone's cosmic ray lab when I was a graduate student. He was one of the greatest leaders I've ever known, while remaining so calm and solid and just plain deep. Principal scientist on Voyager, later head of the JPL, then the TMT and much more. An amazing, inspirational man. So sad to see him go but he had a truly great and influential life. There are few like him.

@arXiv_csRO_bot@mastoxiv.page
2024-04-11 07:16:33

Deep Reinforcement Learning for Mobile Robot Path Planning
Hao Liu, Yi Shen, Shuangjiang Yu, Zijun Gao, Tong Wu
arxiv.org/abs/2404.06974

@Techmeme@techhub.social
2024-04-10 22:55:42

Computer scientist Avi Wigderson wins the 2023 Turing Award for his "foundational contributions to the theory of computation", including his work on randomness (Stephen Ornes/Quanta Magazine)
quantamagazine.org/avi-wigders

@arXiv_csSD_bot@mastoxiv.page
2024-06-14 06:53:10

Vision Transformer Segmentation for Visual Bird Sound Denoising
Sahil Kumar, Jialu Li, Youshan Zhang
arxiv.org/abs/2406.09167

@arXiv_astrophGA_bot@mastoxiv.page
2024-06-14 06:59:30

The turbulent life of NGC 4696 as told by its globular cluster system
S. Federle, M. G\'omez, S. Mieske, W. E. Harris, M. Hilker, I. A. Yegorova, G. L. H. Harris
arxiv.org/abs/2406.08635

@arXiv_astrophIM_bot@mastoxiv.page
2024-06-14 06:59:56

E(2)-Equivariant Features in Machine Learning for Morphological Classification of Radio Galaxies
Natalie E. P. Lines, Joan Font-Quer Roset, Anna M. M. Scaife
arxiv.org/abs/2406.09024

@arXiv_csNI_bot@mastoxiv.page
2024-04-12 06:51:38

UAV-enabled Collaborative Beamforming via Multi-Agent Deep Reinforcement Learning
Saichao Liu, Geng Sun, Jiahui Li, Shuang Liang, Qingqing Wu, Pengfei Wang, Dusit Niyato
arxiv.org/abs/2404.07453

@arXiv_csIT_bot@mastoxiv.page
2024-06-11 06:50:50

Rapid Optimization of Superposition Codes for Multi-Hop NOMA MANETs via Deep Unfolding
Tomer Alter, Nir Shlezinger
arxiv.org/abs/2406.05747

@michabbb@social.vivaldi.net
2024-04-10 10:54:29

How do #LLMs like #ChatGPT work? Explained by Deep-Fake Ryan Gosling using...
youtube.com…

@keithjgrant@front-end.social
2024-06-07 17:25:24

This is a really cool find: Build a Frontend Web Framework from Scratch by Ángel Sola Orbaiceta.
Basically a deep dive into the internals of how a modern frontend framework works. It’s on sale right now at shortener.manning.com/pde2
@…

Cover of Build A Frontend Web Framework from Scratch by Ángel Sola Orbaiceta
@arXiv_mathNA_bot@mastoxiv.page
2024-04-12 08:36:51

This arxiv.org/abs/2212.07737 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_astrophGA_bot@mastoxiv.page
2024-06-14 08:50:22

This arxiv.org/abs/2404.19010 has been replaced.
initial toot: mastoxiv.page/@arXiv_…

@arXiv_eessSP_bot@mastoxiv.page
2024-05-06 06:53:59

A Deep Learning Approach in RIS-based Indoor Localization
Rafael A. Aguiar, Nuno Paulino, Lu\'is M. Pessoa
arxiv.org/abs/2405.01965

@mgorny@social.treehouse.systems
2024-05-06 15:33:39

Today, deep in the woods, my phone suddenly stopped being able to access the Internet. First, I've noticed that the browser couldn't reach any website — but well, reception was poor and websites these days… Then, my railway timetable app couldn't fetch timetables. Okay, poor reception, or maybe they have server problems again.
Later, the reception was better for a while, but things still didn't work. Reception quickly jumped back down, so I blamed it again. And again. Finally, I've figured out this is going for far too long.
I've opened #RethinkDNS and it said "No Internet". I've disabled it temporarily, and everything suddenly started working again. Enabled again, everything's broken. WTF?!
I've dug deeper, and it turned out RethinkDNS apparently lost DNS-over-HTTPS connection… and it never figured out to reconnect on its own, or even give me a meaningful diagnostic. I had to figure out to enter DNS settings, and tap the server tile to make it reconnect.
In the end, it was DNS… but also terrible UX in this program.

@arXiv_eessIV_bot@mastoxiv.page
2024-04-11 08:35:34

This arxiv.org/abs/2404.01102 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_csNE_bot@mastoxiv.page
2024-04-11 07:30:37

Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' Labyrinth
Caleidgh Bayer, Robert J. Smith, Malcolm I. Heywood
arxiv.org/abs/2404.06529 <…

@arXiv_csCL_bot@mastoxiv.page
2024-05-06 08:26:47

This arxiv.org/abs/2403.11894 has been replaced.
initial toot: mastoxiv.page/@arXiv_csCL_…

@arXiv_csIT_bot@mastoxiv.page
2024-06-11 06:50:50

Rapid Optimization of Superposition Codes for Multi-Hop NOMA MANETs via Deep Unfolding
Tomer Alter, Nir Shlezinger
arxiv.org/abs/2406.05747

@arXiv_csRO_bot@mastoxiv.page
2024-06-10 08:45:09

This arxiv.org/abs/2405.05542 has been replaced.
initial toot: mastoxiv.page/@arXiv_csRO_…

@arXiv_astrophSR_bot@mastoxiv.page
2024-05-08 08:43:33

This arxiv.org/abs/2303.08092 has been replaced.
initial toot: mastoxiv.page/@arXiv_…

@jrconlin@soc.jrconlin.com
2024-06-05 17:22:51

I'm very curious what comes of this.
"""
Today, we are investing in the next generation of GenAI security with the 0Day Investigative Network (0Din) by Mozilla, a bug bounty program for large language models (LLMs) and other deep learning technologies. 0Din expands the scope to identify and fix GenAI security by delving beyond the application layer with a focus on emerging classes of vulnerabilities and weaknesses in these new generations of models.
"&…

@arXiv_csLG_bot@mastoxiv.page
2024-05-02 07:17:29

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
arxiv.org/abs/2405.00202

@arXiv_csAR_bot@mastoxiv.page
2024-06-12 06:46:47

vMCU: Coordinated Memory Management and Kernel Optimization for DNN Inference on MCUs
Size Zheng, Renze Chen, Meng Li, Zihao Ye, Luis Ceze, Yun Liang
arxiv.org/abs/2406.06542

@arXiv_physicscompph_bot@mastoxiv.page
2024-04-10 07:27:15

Deep Learning Method for Computing Committor Functions with Adaptive Sampling
Bo Lin, Weiqing Ren
arxiv.org/abs/2404.06206

@arXiv_csCE_bot@mastoxiv.page
2024-05-07 07:20:11

Deep Reinforcement Learning for Modelling Protein Complexes
Tao Feng, Ziqi Gao, Jiaxuan You, Chenyi Zi, Yan Zhou, Chen Zhang, Jia Li
arxiv.org/abs/2405.02299

@arXiv_physicsfludyn_bot@mastoxiv.page
2024-06-10 07:05:48

Modulation instability in dispersive parity-broken systems
Sudheesh Srivastava, Gustavo M. Monteiro, Sriram Ganeshan
arxiv.org/abs/2406.04570

@arXiv_physicschemph_bot@mastoxiv.page
2024-04-11 07:11:55

Propensity of water self-ions at air(oil)-water interfaces revealed by deep potential molecular dynamics with enhanced sampling
Pengchao Zhang, Axel Tosello Gardini, Xuefei Xu
arxiv.org/abs/2404.07027

@deprogrammaticaipsum@mas.to
2024-05-02 07:09:01

"By 1973, the first volume of the defining work of our craft, “The Art of Computer Programming” had been available in bookstores since 1968, and its first chapter literally consisted of a 100-something page long introduction to various mathematical concepts. Induction, logarithms, series, matrices, elementary number theory, permutations and factorials, Fibonacci numbers, are some of the subjects exposed in those beautifully typeset pages."

@arXiv_mathOC_bot@mastoxiv.page
2024-05-09 08:38:29

This arxiv.org/abs/2308.11925 has been replaced.
initial toot: mastoxiv.page/@arXiv_mat…

@arXiv_csRO_bot@mastoxiv.page
2024-06-10 07:24:26

Sim-to-real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning
Arvi Jonnarth, Ola Johansson, Michael Felsberg
arxiv.org/abs/2406.04920

@arXiv_csCR_bot@mastoxiv.page
2024-05-07 08:44:29

This arxiv.org/abs/2402.06357 has been replaced.
initial toot: mastoxiv.page/@arXiv_csCR_…

@ethanwhite@hachyderm.io
2024-05-30 16:57:37

"While not all paper mills are AI-based, it's just too easy to use AI to meet the perverse incentives of the present academic publishing ecosystem." - @…
By refusing for decades to address the underlying issues related to academic incentives we have definitely put ourselves in a situation where LLMs pose a serious threat to scholarly work. …

@arXiv_condmatquantgas_bot@mastoxiv.page
2024-06-05 07:31:50

Rabi Oscillation of High Partial Wave Interacting Atoms in Deep Optical Lattice
Zeqing Wang, Ran Qi
arxiv.org/abs/2406.02136

@arXiv_condmatdisnn_bot@mastoxiv.page
2024-05-08 07:21:57

A simple theory for training response of deep neural networks
Kenichi Nakazato
arxiv.org/abs/2405.04074 arxiv.org/pdf…

@arXiv_csMA_bot@mastoxiv.page
2024-06-06 06:50:42

Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning
Dom Huh, Prasant Mohapatra
arxiv.org/abs/2406.02890

@arXiv_csHC_bot@mastoxiv.page
2024-04-30 07:24:33

How Deep Is Your Gaze? Leveraging Distance in Image-Based Gaze Analysis
Maurice Koch, Nelusa Pathmanathan, Daniel Weiskopf, Kuno Kurzhals
arxiv.org/abs/2404.18680

@arXiv_csSD_bot@mastoxiv.page
2024-06-07 07:18:26

SilentCipher: Deep Audio Watermarking
Mayank Kumar Singh, Naoya Takahashi, Weihsiang Liao, Yuki Mitsufuji
arxiv.org/abs/2406.03822 <…

@jrconlin@soc.jrconlin.com
2024-06-05 17:22:51

I'm very curious what comes of this.
"""
Today, we are investing in the next generation of GenAI security with the 0Day Investigative Network (0Din) by Mozilla, a bug bounty program for large language models (LLMs) and other deep learning technologies. 0Din expands the scope to identify and fix GenAI security by delving beyond the application layer with a focus on emerging classes of vulnerabilities and weaknesses in these new generations of models.
"&…

@arXiv_csLG_bot@mastoxiv.page
2024-05-02 07:17:29

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
arxiv.org/abs/2405.00202

@arXiv_eessSP_bot@mastoxiv.page
2024-05-08 07:16:22

Deep Reinforcement Learning for Multi-User RF Charging with Non-linear Energy Harvesters
Amirhossein Azarbahram, Onel L. A. L\'opez, Petar Popovski, Shashi Raj Pandey, Matti Latva-aho
arxiv.org/abs/2405.04218

@arXiv_csMM_bot@mastoxiv.page
2024-04-23 07:14:11

Deep Learning-based Text-in-Image Watermarking
Bishwa Karki, Chun-Hua Tsai, Pei-Chi Huang, Xin Zhong
arxiv.org/abs/2404.13134

@inthehands@hachyderm.io
2024-04-18 02:45:19

Keep repeating it: supposed “AI detectors” are snake oil. Pure scam. Worse than nothing.
Do not use, period. Not as a starting point. Not in combination with other processes or tools.
• Do • not • use •
mastodon.social/@dangillmor/11

@arXiv_csAR_bot@mastoxiv.page
2024-06-11 06:46:57

Evaluation of Posits for Spectral Analysis Using a Software-Defined Dataflow Architecture
Sameer Deshmukh, Daniel Khankin, William Killian, John Gustafson, Elad Raz
arxiv.org/abs/2406.05398

@sean@scoat.es
2024-05-25 17:51:22

In the late ‘90s and early 2000s, people—regular people—were often afraid of ecommerce and open source software.
We did a ton of work to build trust in both of these things, to the point where they became the obvious defaults when people had a choice.
It really hurts me deep within to see “us” cashing out the trust we’ve built in the web for the short term profits of bad and unreliable search, cheap engagement tricks, and completely ignorant “hallucinations”.

@arXiv_mathNA_bot@mastoxiv.page
2024-06-11 09:13:46

This arxiv.org/abs/2311.16167 has been replaced.
initial toot: mastoxiv.page/@arXiv_mat…

@arXiv_condmatmtrlsci_bot@mastoxiv.page
2024-05-08 07:32:45

Molecular Identification via Molecular Fingerprint extraction from Atomic Force Microscopy images
Manuel Gonz\'alez Lastre, Pablo Pou, Miguel Wiche, Daniel Ebeling, Andre Schirmeisen, Rub\'en P\'erez
arxiv.org/abs/2405.04321

@arXiv_qfinPM_bot@mastoxiv.page
2024-05-06 07:22:14

Portfolio Management using Deep Reinforcement Learning
Ashish Anil Pawar, Vishnureddy Prashant Muskawar, Ritesh Tiku
arxiv.org/abs/2405.01604

@arXiv_statML_bot@mastoxiv.page
2024-05-02 07:20:22

From Empirical Observations to Universality: Dynamics of Deep Learning with Inputs Built on Gaussian mixture
Jaeyong Bae, Hawoong Jeong
arxiv.org/abs/2405.00642

@arXiv_mathOC_bot@mastoxiv.page
2024-05-09 08:38:29

This arxiv.org/abs/2308.11925 has been replaced.
initial toot: mastoxiv.page/@arXiv_mat…

@arXiv_qbioQM_bot@mastoxiv.page
2024-06-06 07:29:06

Modeling PROTAC Degradation Activity with Machine Learning
Stefano Ribes, Eva Nittinger, Christian Tyrchan, Roc\'io Mercado
arxiv.org/abs/2406.02637

@cosmos4u@scicomm.xyz
2024-05-16 22:53:13

NASA and ESA have signed an agreement to expand NASA’s work on the #ExoMars Rosalind Franklin rover, an ESA-led mission launching in 2028 that will search for signs of ancient life on the Red Planet: nasa.gov/news-release/nasa-eur - NASA will procure a U.S. commercial launch provider and will provide heater units and elements of the propulsion system needed to land on Mars, and a new instrument on the rover will be the first drill to a depth of up to 2 meters deep below the surface.

@arXiv_csCE_bot@mastoxiv.page
2024-05-08 08:31:49

This arxiv.org/abs/2405.02299 has been replaced.
initial toot: mastoxiv.page/@arXiv_csCE_…

@arXiv_csLO_bot@mastoxiv.page
2024-04-26 07:12:26

Derandomization with Pseudorandomness
Emin Karayel
arxiv.org/abs/2404.16614 arxiv.org/pdf/2404.16614

@arXiv_csET_bot@mastoxiv.page
2024-06-04 09:09:00

This arxiv.org/abs/2401.16072 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_csCY_bot@mastoxiv.page
2024-05-02 08:26:58

This arxiv.org/abs/2209.11200 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_astrophIM_bot@mastoxiv.page
2024-05-10 07:00:10

Transformer neural networks for closed-loop adaptive optics using non-modulated pyramid wavefront sensors
Camilo Weinberger, Jorge Tapia, Benoit Neichel, Esteban Vera
arxiv.org/abs/2405.05472

@arXiv_eessIV_bot@mastoxiv.page
2024-06-05 08:46:44

This arxiv.org/abs/2401.15613 has been replaced.
initial toot: mastoxiv.page/@arXiv_ees…

@arXiv_csRO_bot@mastoxiv.page
2024-06-03 07:25:18

An Organic Weed Control Prototype using Directed Energy and Deep Learning
Deng Cao, Hongbo Zhang, Rajveer Dhillon
arxiv.org/abs/2405.21056

@arXiv_physicscompph_bot@mastoxiv.page
2024-04-10 07:27:14

Computing Transition Pathways for the Study of Rare Events Using Deep Reinforcement Learning
Bo Lin, Yangzheng Zhong, Weiqing Ren
arxiv.org/abs/2404.05905

@arXiv_csCR_bot@mastoxiv.page
2024-05-06 07:22:36

Adversarial Attacks on Reinforcement Learning Agents for Command and Control
Ahaan Dabholkar, James Z. Hare, Mark Mittrick, John Richardson, Nicholas Waytowich, Priya Narayanan, Saurabh Bagchi
arxiv.org/abs/2405.01693

@arXiv_csSD_bot@mastoxiv.page
2024-04-10 07:12:53

A Novel Bi-LSTM And Transformer Architecture For Generating Tabla Music
Roopa Mayya, Vivekanand Venkataraman, Anwesh P R, Narayana Darapaneni
arxiv.org/abs/2404.05765

@arXiv_physicsfludyn_bot@mastoxiv.page
2024-04-30 07:21:45

Exploring the efficacy of a hybrid approach with modal decomposition over fully deep learning models for flow dynamics forecasting
Rodrigo Abad\'ia-Heredia, Adri\'an Corrochano, Manuel Lopez-Martin, Soledad Le Clainche
arxiv.org/abs/2404.17884

@arXiv_csRO_bot@mastoxiv.page
2024-06-04 07:23:00

Evaluating MEDIRL: A Replication and Ablation Study of Maximum Entropy Deep Inverse Reinforcement Learning for Human Social Navigation
Vinay Gupta (Purdue University), Nihal Gunukula (Purdue University)
arxiv.org/abs/2406.00968

@arXiv_condmatdisnn_bot@mastoxiv.page
2024-05-08 07:22:03

Neural network based deep learning analysis of semiconductor quantum dot qubits for automated control
Jacob R. Taylor, Sankar Das Sarma
arxiv.org/abs/2405.04524

@arXiv_eessIV_bot@mastoxiv.page
2024-06-05 08:46:44

This arxiv.org/abs/2401.15613 has been replaced.
initial toot: mastoxiv.page/@arXiv_ees…

@arXiv_eessSP_bot@mastoxiv.page
2024-06-07 08:53:23

This arxiv.org/abs/2305.02744 has been replaced.
initial toot: mastoxiv.page/@arXiv_ees…

@arXiv_csRO_bot@mastoxiv.page
2024-06-04 07:23:00

Evaluating MEDIRL: A Replication and Ablation Study of Maximum Entropy Deep Inverse Reinforcement Learning for Human Social Navigation
Vinay Gupta (Purdue University), Nihal Gunukula (Purdue University)
arxiv.org/abs/2406.00968

@arXiv_csNI_bot@mastoxiv.page
2024-05-31 07:32:47

Data Service Maximization in Integrated Terrestrial-Non-Terrestrial 6G Networks: A Deep Reinforcement Learning Approach
Nway Nway Ei, Kitae Kim, Yan Kyaw Tun, Choong Seon Hong
arxiv.org/abs/2405.19771

@arXiv_csHC_bot@mastoxiv.page
2024-04-30 08:33:55

This arxiv.org/abs/2307.05370 has been replaced.
initial toot: mastoxiv.page/@arXiv_csHC_…

@arXiv_csCY_bot@mastoxiv.page
2024-05-02 08:26:58

This arxiv.org/abs/2209.11200 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_physicsfludyn_bot@mastoxiv.page
2024-04-30 07:21:45

Exploring the efficacy of a hybrid approach with modal decomposition over fully deep learning models for flow dynamics forecasting
Rodrigo Abad\'ia-Heredia, Adri\'an Corrochano, Manuel Lopez-Martin, Soledad Le Clainche
arxiv.org/abs/2404.17884

@arXiv_csCE_bot@mastoxiv.page
2024-04-22 06:47:11

FinLangNet: A Novel Deep Learning Framework for Credit Risk Prediction Using Linguistic Analogy in Financial Data
Yu Lei, Zixuan Wang, Chu Liu, Tongyao Wang, Dongyang Lee
arxiv.org/abs/2404.13004

@arXiv_csSD_bot@mastoxiv.page
2024-06-06 07:15:11

Generalized Fake Audio Detection via Deep Stable Learning
Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Yuankun Xie, Yukun Liu, Xiaopeng Wang, Xuefei Liu, Yongwei Li, Jianhua Tao, Yi Lu, Xin Qi, Shuchen Shi
arxiv.org/abs/2406.03237

@arXiv_csRO_bot@mastoxiv.page
2024-05-31 06:53:17

Image-to-Joint Inverse Kinematic of a Supportive Continuum Arm Using Deep Learning
Shayan Sepahvand, Guanghui Wang, Farrokh Janabi-Sharifi
arxiv.org/abs/2405.20248

@arXiv_astrophIM_bot@mastoxiv.page
2024-04-29 07:24:43

Star-Image Centering with Deep Learning II: HST/WFPC2 Full Field of View
Dana I. Casetti-Dinescu, Roberto Baena-Galle, Terrence M. Girard, Alejandro Cervantes-Rovira, Sebastian Todeasa
arxiv.org/abs/2404.16995

@arXiv_astrophGA_bot@mastoxiv.page
2024-06-03 07:29:06

HOLISMOKES XIII: Strong-lens candidates at all mass scales and their environments from the Hyper-Suprime Cam and deep learning
Stefan Schuldt, Raoul Canameras, Irham T. Andika, Satadru Bag, Alejandra Melo, Yiping Shu, Sherry H. Suyu, Stefan Taubenberger, Claudio Grillo
arxiv.org/abs/2405.20383

@arXiv_mathNA_bot@mastoxiv.page
2024-06-07 08:59:12

This arxiv.org/abs/2402.04610 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_physicscompph_bot@mastoxiv.page
2024-06-10 07:12:26

Physics-Informed Neural Networks for the Numerical Modeling of Steady-State and Transient Electromagnetic Problems with Discontinuous Media
Michel Nohra, Steven Dufour
arxiv.org/abs/2406.04380

@arXiv_csNI_bot@mastoxiv.page
2024-05-31 07:32:47

Data Service Maximization in Integrated Terrestrial-Non-Terrestrial 6G Networks: A Deep Reinforcement Learning Approach
Nway Nway Ei, Kitae Kim, Yan Kyaw Tun, Choong Seon Hong
arxiv.org/abs/2405.19771

@arXiv_csRO_bot@mastoxiv.page
2024-06-04 07:23:21

Deep Stochastic Kinematic Models for Probabilistic Motion Forecasting in Traffic
Laura Zheng, Sanghyun Son, Jing Liang, Xijun Wang, Brian Clipp, Ming C. Lin
arxiv.org/abs/2406.01431

@arXiv_eessIV_bot@mastoxiv.page
2024-05-01 06:54:02

Automatic Cardiac Pathology Recognition in Echocardiography Images Using Higher Order Dynamic Mode Decomposition and a Vision Transformer for Small Datasets
Andr\'es Bell-Navas, Nourelhouda Groun, Mar\'ia Villalba-Orero, Enrique Lara-Pezzi, Jes\'us Garicano-Mena, Soledad Le Clainche
arxiv.org/abs/2404.19579 arxiv.org/pdf/2404.19579
arXiv:2404.19579v1 Announce Type: new
Abstract: Heart diseases are the main international cause of human defunction. According to the WHO, nearly 18 million people decease each year because of heart diseases. Also considering the increase of medical data, much pressure is put on the health industry to develop systems for early and accurate heart disease recognition. In this work, an automatic cardiac pathology recognition system based on a novel deep learning framework is proposed, which analyses in real-time echocardiography video sequences. The system works in two stages. The first one transforms the data included in a database of echocardiography sequences into a machine-learning-compatible collection of annotated images which can be used in the training stage of any kind of machine learning-based framework, and more specifically with deep learning. This includes the use of the Higher Order Dynamic Mode Decomposition (HODMD) algorithm, for the first time to the authors' knowledge, for both data augmentation and feature extraction in the medical field. The second stage is focused on building and training a Vision Transformer (ViT), barely explored in the related literature. The ViT is adapted for an effective training from scratch, even with small datasets. The designed neural network analyses images from an echocardiography sequence to predict the heart state. The results obtained show the superiority of the proposed system and the efficacy of the HODMD algorithm, even outperforming pretrained Convolutional Neural Networks (CNNs), which are so far the method of choice in the literature.

@arXiv_csRO_bot@mastoxiv.page
2024-06-04 07:23:21

Deep Stochastic Kinematic Models for Probabilistic Motion Forecasting in Traffic
Laura Zheng, Sanghyun Son, Jing Liang, Xijun Wang, Brian Clipp, Ming C. Lin
arxiv.org/abs/2406.01431

@arXiv_mathNA_bot@mastoxiv.page
2024-06-07 08:59:12

This arxiv.org/abs/2402.04610 has been replaced.
link: scholar.google.com/scholar?q=a

@arXiv_astrophGA_bot@mastoxiv.page
2024-04-29 07:24:24

Extreme Emission-Line Galaxies in the MUSE Hubble Ultra Deep Field Survey
I. del Moral-Castro, J. M. V\'ilchez, J. Iglesias-P\'aramo, A. Arroyo-Polonio
arxiv.org/abs/2404.17415

@arXiv_csRO_bot@mastoxiv.page
2024-05-07 08:52:06

This arxiv.org/abs/2403.05771 has been replaced.
initial toot: mastoxiv.page/@arXiv_csRO_…

@arXiv_astrophGA_bot@mastoxiv.page
2024-05-06 07:29:42

The JWST EXCELS survey: Too much, too young, too fast? Ultra-massive quiescent galaxies at 3 < z < 5
A. C. Carnall, F. Cullen, R. J. McLure, D. J. McLeod, R. Begley, C. T. Donnan, J. S. Dunlop, A. E. Shapley, K. Rowlands, O. Almaini, K. Z. Arellano-C\'ordova, L. Barrufet, A. Cimatti, R. S. Ellis, N. A. Grogin, M. L. Hamadouche, G. D. Illingworth, A. M. Koekemoer, H. -H. Leung, C. C. Lovell, P. G. P\'erez-Gonz\'alez, P. Santini, T. M. Stanton, V. Wild

@arXiv_csRO_bot@mastoxiv.page
2024-05-06 06:52:39

Panoptic-SLAM: Visual SLAM in Dynamic Environments using Panoptic Segmentation
Gabriel Fischer Abati, Jo\~ao Carlos Virgolino Soares, Vivian Suzano Medeiros, Marco Antonio Meggiolaro, Claudio Semini
arxiv.org/abs/2405.02177

@arXiv_csRO_bot@mastoxiv.page
2024-06-03 08:37:36

This arxiv.org/abs/2405.00515 has been replaced.
initial toot: mastoxiv.page/@arXiv_csRO_…

@arXiv_csRO_bot@mastoxiv.page
2024-05-02 07:32:45

GAD-Generative Learning for HD Map-Free Autonomous Driving
Weijian Sun, Yanbo Jia, Qi Zeng, Zihao Liu, Jiang Liao, Yue Li, Xianfeng Li, Bolin Zhao
arxiv.org/abs/2405.00515

@arXiv_csRO_bot@mastoxiv.page
2024-05-01 06:52:26

Transformer-Enhanced Motion Planner: Attention-Guided Sampling for State-Specific Decision Making
Lei Zhuang, Jingdong Zhao, Yuntao Li, Zichun Xu, Liangliang Zhao, Hong Liu
arxiv.org/abs/2404.19403