Valeriy M., PhD, MBA, CQF @predict_addict
PhD in machine learning | conformal prediction | time-series | author of bestselling Practical Guide to Applied Conformal-Prediction https://t.co/ugR9TtXd29 github.com/valeman/awesom… London Joined November 2021-
Tweets13K
-
Followers17K
-
Following3K
-
Likes9K
(4/4) Our work paves way for more meaningful image reconstruction bounds and expands our toolkit to safely deploy novel imaging systems and algorithms IRL 🤩. Lots of opportunities to evaluate image quality for other applications like diagnosis. Code: github.com/matthewyccheun…
(3/4) Our method is nothing without meaningful application. Thx to @LaurenceECourt @nethertonians , we demonstrate our method for radiotherapy planning w/ RPA (FDA-cleared) using sparse-view CT. RPA improves planning access for low-middle income countries! rpa.mdanderson.org
(2/4) We calibrate on downstream metrics to retrieve upper/lower bound reconstructions and statistical inliers/outliers. Our reconstructions are now 1) meaningful IRL and 2) guided by statistical guarantees to contain ground truth. Thanks to the power of #conformalprediction!
How can we ensure image reconstructions are trustworthy? One way is to provide upper/lower bounds. We propose a principled way to attain reconstruction bounds based on statistical guarantees of downstream metrics. w/ @nethertonians @LaurenceECourt arxiv.org/abs/2404.15274 🧵1/4
How can we ensure image reconstructions are trustworthy? One way is to provide upper/lower bounds. We propose a principled way to attain reconstruction bounds based on statistical guarantees of downstream metrics. w/ @nethertonians @LaurenceECourt arxiv.org/abs/2404.15274 🧵1/4
5/N From the algorithmic aspect: KANs and MLPs are dual in the sense that -- MLPs have (usually fixed) activation functions on neurons, while KANs have (learnable) activation functions on weights. These 1D activation functions are parameterized as splines.
Sebastian Raschka @rasbt
267K Followers 906 Following Machine learning & AI researcher writing at https://t.co/A0tXWzG1p5. LLM research engineer @LightningAI. Previously stats professor at UW-Madison.
Christoph Molnar @ChristophMolnar
30K Followers 1K Following Author of Interpretable Machine Learning https://t.co/gJKlTA2deP | Newsletter: https://t.co/6fQuMr8yI8
Anastasios Nikolas An.. @ml_angelopoulos
3K Followers 785 Following @Berkeley_EECS Ph.D. with Mike Jordan/Jitendra Malik. Conformal prediction, distribution-free uncertainty quantification, vision/imaging. Former @stanford_ee.
abhishek @abhi1thakur
81K Followers 664 Following 🤗 I build AutoTrain @huggingface 👨🏽💻 World's First 4x Grand Master @kaggle 🎥 YouTube 100k+: https://t.co/BHnem8fTu5 ⭐ GitHub Star
Delip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈
Matt Harrison @__mharrison__
158K Followers 892 Following Python 🐍 + Data Science 🚀 trainer @__metasnake__ 🦜 Speaker ✍ Author 👨🏫 Instructor (@Stanford) 📣 DM for Sponsorship
Tivadar Danka @TivadarDanka
66K Followers 456 Following I make math accessible for everyone. Mathematician with an INTJ personality. Chaotic good. Writing https://t.co/jYkO4bz6lL
Miles Cranmer @MilesCranmer
12K Followers 903 Following Assistant Prof @Cambridge_Uni, works on AI for the physical sciences. Previously: Flatiron, DeepMind, Princeton, McGill.
Martin Görner @martin_gorner
12K Followers 6K Following Product Manager for Keras and Tensorflow high-level APIs. Previously worked on Cloud TPUs (Tensor Processing Units). Passionate about democratizing ML.
Maarten van Smeden @MaartenvSmeden
42K Followers 837 Following Statistician • associate prof • statistics/epidemiology/AI methodology, Julius Center @umcutrecht • own views
Datta Meher @DattaMeher
0 Followers 177 Following
raman shariati @RamanShariati
32 Followers 320 Following A jacked nerd. interested in AI(agent nets) & BIOTECH(universal assemblers)
Denis Bykov @denis_bykov
144 Followers 608 Following Search @ Yango Maps. Leading talented minds in crafting innovative search engines.
Rainman @0xRainMan_
50 Followers 155 Following Just me talking to myself about myself mostly. Don't mind me. Opinions expressed are highly personal.
Lute Lillo Portero @Lute47Lillo
186 Followers 502 Following 👨🏼💻🇺🇸 AI PhD Student at @uvmvermont @OmahaMSOC alumni 📍Burlington, VT - El Altet, Alicante🏡
u' @dreammbb
365 Followers 102 Following
Carlos David @CarlosDZam
187 Followers 3K Following Futuro científico, me encanta el cine y los libros. Future scientist, I love the books and the movies.
Diego Loza @fznumber
10 Followers 477 Following
Léo Aparisi de Lanno.. @LeoAparisidL
842 Followers 3K Following PhD student @UChi_Economics. Economics/History/Politics/Whatever.
علي حداد @9LkVSi8E3NWf19q
28 Followers 562 Following
Unesd @YNess97
113 Followers 2K Following
Matt Y. Cheung @matte_ce
64 Followers 146 Following PhD Student @RiceUniversity. CV+ML+ECE for safe and fair MedTech. Current interest: Uncertainty Quant. @ucdavis alum. Own views.
Ronak Pradhan @RonakPradhan15
2 Followers 19 Following
Breaking Markets @sentimarkets
93 Followers 1K Following Best source of intelligence for stocks, not financial advice.
Aaditya ; @Aaditya26082004
535 Followers 7K Following CS'26 • Machine Learning • Open-Source • Web Dev. • Algorithms • Jai Shree Krishna 🦚🪈
Fatmatulzehra Uslu @FzehrausluUslu
49 Followers 535 Following Ass. Prof at Bursa Technical University. Phd @ Imperial College London. Interested in medical image analysis, deep learning
Katso John Obotsang @Katso_Obotsang
42 Followers 208 Following Quantum Computing Research🌐 | ML & Deep Neural Networks 💻 | Robotics 🚀 | Theoretical Physics ⚛📚 |
Jonthavo @jonthavo
46 Followers 182 Following
⋉ 의현 @EEEuihyun
372 Followers 1K Following researcher, mathematician, qu_eee_r, sound producer candidate, mainly interested in Geometry & Topology, https://t.co/JG6XOjJguO.pax
Razvan Marinescu @RazMarinescu
1K Followers 2K Following #MachineLearning #CompBio #MedicalImaging. Assist. Prof. in CSE @UCSC. Co-founder @GiwoTech.
หารวิมล @IR4ZctKEaMwa3GY
68 Followers 1K Following หากคุณชอบฉันและสนใจสามารถติดตามฉันได้และฉันจะอัปเดตข้อมูลติดต่อหน้าแรกของฉันเป็นครั้งคราว
Priyam kakati @Priyamkakati46
30 Followers 758 Following Full stack data scientist @kornferry|| Equity investor || MLops || 14K+ LinkedIn 📈 || Follow me on linkedin! 👇🏼
Mariano Devita @mariano_devita
4 Followers 166 Following
Jonas Frost @soziojonas
71 Followers 729 Following Graduate student of sociology at @UniLeipzig Interests in #RationalChoice #stats #rprogramming #webscraping #networkanalysis #casualinference
Isabella Stevens @stevens86708
1 Followers 3 Following
静默zzz @sss49627598
0 Followers 20 Following
k.koyama @k_kyo_hey
205 Followers 974 Following Home is where the heart is. DONE IS BETTER THAN PERFECT
Electronicsseeker @libertarian108
10 Followers 2K Following
valentin @software_valen
13 Followers 96 Following software engineer — laburo como machine learning engineer
Dr. Shahnawaz Ahmed @quantshah
790 Followers 909 Following Deep learning researcher @ https://t.co/elSx10ayqG. PhD in applied quantum physics (ML applied to quantum) from Chalmers University of Technology, Sweden.
Hamed Hassani @HamedSHassani
2K Followers 669 Following Associate Professor, University of Pennsylvania @PENN, Machine Learning, Information Theory
Mrwhosetheboss @iamnayr13
134 Followers 1K Following
Market Mastermind - N.. @D_Master_Mind
3K Followers 437 Following Stock Market Analysis is my passion. Market related tweets are not trading recommendations. Personal opinion only. Not SEBI Reg. Consult your Financial Advisor
Sebastian Raschka @rasbt
267K Followers 906 Following Machine learning & AI researcher writing at https://t.co/A0tXWzG1p5. LLM research engineer @LightningAI. Previously stats professor at UW-Madison.
Yann LeCun @ylecun
712K Followers 719 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
Bojan Tunguz @tunguz
187K Followers 8K Following Machine Learning ex Nvidia. Kaggle Quadruple Grandmaster. Data Scientist. Physicist. Catholic. Husband. Father. Stanford Alum. e/xgb. XGBoost.eth. AMDG.
Mark Tenenholtz @marktenenholtz
115K Followers 546 Following Head of AI @PredeloHQ. XGBoost peddler, transformer purveyor.
Christoph Molnar @ChristophMolnar
30K Followers 1K Following Author of Interpretable Machine Learning https://t.co/gJKlTA2deP | Newsletter: https://t.co/6fQuMr8yI8
AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80Gx
elvis @omarsar0
189K Followers 486 Following Building with LLMs @dair_ai • Prev: Meta AI, Galactica LLM, PapersWithCode, Elastic, PhD • Creator of the Prompting Guide (~4M learners)
Gabriel Peyré @gabrielpeyre
92K Followers 449 Following @CNRS researcher at @ENS_ULM. One tweet a day on computational mathematics.
Kevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.
Peyman Milanfar @docmilanfar
67K Followers 264 Following Distinguished Scientist at Google Research. Computational Imaging, Machine Learning, and Vision. Tweets = personal opinions. May change or disappear over time.
Yi Ma @YiMaTweets
71K Followers 123 Following Chair Professor in AI, Director of IDS, Head of CS, HKU; Professor of EECS, Berkeley; Author of Book: High-Dim Data Analysis, https://t.co/gwaqMJp8av.
Google DeepMind @GoogleDeepMind
944K Followers 275 Following We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
Frank Nielsen @FrnkNlsn
23K Followers 1K Following Machine Learning & AI, Information Sciences & Information Geometry, Distances & Statistical models, HPC. "Geometry defines the architecture of spaces" @SonyCSL
Alfredo Canziani @alfcnz
86K Followers 268 Following Musician, math lover, cook, dancer, 🏳️🌈, and an ass prof of Computer Science at New York University
Jim Fan @DrJimFan
230K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.
PyTorch @PyTorch
380K Followers 77 Following Tensors and neural networks in Python with strong hardware acceleration. PyTorch is an open source project at the Linux Foundation. #PyTorchFoundation
Kosta Derpanis @CSProfKGD
48K Followers 197 Following #CS Associate Prof @YorkUniversity, #ComputerVision Scientist Samsung #AI, @VectorInst Faculty Affiliate, TPAMI AE, #CVPR2024/#ECCV2024 Publicity Co-chair
Matt Y. Cheung @matte_ce
64 Followers 146 Following PhD Student @RiceUniversity. CV+ML+ECE for safe and fair MedTech. Current interest: Uncertainty Quant. @ucdavis alum. Own views.
Max Pontryagin @MaxPontryagin
257 Followers 2K Following Statistician, data scientist #mathematics #optimization #dynamicalSystems #RandomMatrixTheory #signal_processing
Rex "garbage in" Doug.. @RexDouglass
4K Followers 5K Following Applied Scientist in Industry. Previously UCSD. Princeton PhD.
gavin leech @g_leech_
4K Followers 420 Following the subject of criticism @ArbResearch, @Bristol_AI_CDT, ESPR
Jonte Dancker @JDancker
76 Followers 93 Following
Razvan Marinescu @RazMarinescu
1K Followers 2K Following #MachineLearning #CompBio #MedicalImaging. Assist. Prof. in CSE @UCSC. Co-founder @GiwoTech.
Federico Cabitza @cabitzaf
1K Followers 77 Following An interactionist studying Human-AI teaming in decision making; Assoc. Professor of Human-AI Interaction and DSS @ University of Milano-Bicocca, Italy.
Alex Robey @AlexRobey23
621 Followers 849 Following Ph.D. student at @Penn studying robust machine learning. Formerly @GoogleAI, @Livermore_Lab | B.S. & B.A. from @swarthmore
Guillermo Santamaría.. @alveuz
616 Followers 1K Following Data Scientist. Interested in ML, Complex Systems, Entropy and data-driven solutions. Collector of sounds and music for doing DSc (https://t.co/ILTrUyU5UR)
near @nearcyan
46K Followers 882 Following https://t.co/IdaJwZJCXm partner @ https://t.co/9g1MIgjiqc dms open
Hamed Hassani @HamedSHassani
2K Followers 669 Following Associate Professor, University of Pennsylvania @PENN, Machine Learning, Information Theory
Accepted papers at TM.. @TmlrPub
3K Followers 2 Following
David Roth-Lindberg @RothLindberg
15K Followers 4K Following International SEO Specialist, China consultant. Posting mostly about hypocrisy and moral cowardice. Visit my RedBubble store at https://t.co/nPkPexWXW1
Dan Collins @DanCollins2011
12K Followers 2K Following Founder@Hippogriff Data Security Founder@Tyrell Medical YouTube Channel: Chaos Inc Engineer/20 years in China
Megatron @Megatron_ron
285K Followers 1K Following Breaking news | Geopolitics | War monitoring Support: https://t.co/z52M4ovE0C | https://t.co/JsTMGFACtV Tgram: https://t.co/hI2fMt3CAZ
Lee Camp [Redacted] @LeeCamp
222K Followers 15K Following Most censored comedian in America—Former host of Redacted Tonight—Livestreams 4 days week at Rumble dot com slash LeeCamp
Hyeok Kim @hyeok__kim
771 Followers 178 Following PhD Student at @northwesterncs. Interested in making vis alive. ☮️ Learning ASL. (In the job market)
Gordon Gekko @GordonGekko420
7K Followers 369 Following I love formatting power points | Debating paying to make myself Forbes 30 under 30 | 25,000+ lifetime Chick-fil-a points | satire | Sesh Code: GREEDISGOOD
Negar @n3gRain
247 Followers 324 Following #BlackLivesMatter Marathoner | Generative AI | Human + AI
François Fleuret @francoisfleuret
31K Followers 456 Following Prof. @Unige_en, Adjunct Prof. @EPFL_en, Research Fellow @idiap_ch, co-founder @nc_shape. AI and machine learning since 1994. I like reality.
Leo Gorodinski @eulerfx
1K Followers 634 Following Co-Founder / CTO https://t.co/ULhUdcCcQH @AlvysTeam, former engineer @JetTechnology
Luke Kim @0xLukeKim
2K Followers 916 Following Founder and CEO of @spice_ai. Previously co-created Azure Incubations with @markussinovich and built @daprdev, https://t.co/uC1VCzgZHY (Radius), and more!
Eser Sekercioglu @EserSekercioglu
59 Followers 65 Following Data Scientist, Political Scientist, nature enthusiast...
Jorge de la Torre @Jorgede70926160
17 Followers 92 Following Professor at Electric Engineering Department at UAZ (@NotiUAZ). Nanotecnology, renewable energy and machine learning.
whitemonkey1 @babywhitemonkey
1K Followers 2K Following Follower of @Tianxiashunv PARODY / SATIRE / JOKES / POLITICAL COMMENTARY .. Feel free to use any AI generated images i made.. No DM Please
Pongsiri Huang @HuangPongs97222
18 Followers 60 Following
Alex Carriero @alcarriero
30 Followers 52 Following
dasmodeler @dasmodeler
829 Followers 413 Following Mathematician by training, data scientist by trade. Tweets are my own, RTs not endorsement. #data #climate #esg #finance #math #politics #risk #tech
The Gradient @gradientpub
21K Followers 16 Following The Gradient cuts through the hype and the cynicism to provide accessible, sophisticated reporting on the latest AI research. https://t.co/XJqypG82jD
Jenna Landy @naive_bae
34 Followers 137 Following
Clown World ™ 🤡 @ClownWorld_
2.4M Followers 502 Following Official #ClownWorld ™ 🤡 #NoCaptionNeeded ** DM us for removals/credit
Gergely Orosz @GergelyOrosz
249K Followers 2K Following Writing @Pragmatic_Eng, the #1 technology newsletter on Substack. Author of @EngGuidebook. Formerly Uber & Skype.
sumtyme.ai @twentyonenot2
18 Followers 107 Following Foundational AI startup focused on financial time series forecasting.
Min Choi @minchoi
66K Followers 763 Following AI Educator. 𝕏 about AI, solutions and interesting things. Showing how to leverage AI in practical ways for you and your business.
Charlie Marx @CharlieTMarx
285 Followers 402 Following CS PhD student @Stanford. Machine learning, statistics, fairness and interpretability in AI.
Shachi Deshpande @ShachiDeshpande
35 Followers 133 Following PhD Candidate at Cornell Tech, NYC. Interested in Causal Inference and Machine Learning
Shroff Publishers @shroffpub
356 Followers 403 Following
Djole 🇷🇸 @onlydjole
38K Followers 4K Following 🌐 I untie 'Gordian knots'. I drive too 'smart people' crazy. Stop nazism and fascism! 🇷🇸Развезујем 'Гордијеве чворове'. Излуђујем 'препаметне'. Стоп нацизму!
camilo @AscendedYield
8K Followers 447 Following international macroeconomics enjoyer • MATLAB sufferer • BSc Financial Mathematics, MSc Economics • 🇬🇧🚀
Seyed Mohammad Marand.. @s_m_marandi
148K Followers 221 Following Professor of English Literature and Orientalism, University of Tehran سید محمد مرندی، استاد ادبیات انگلیسی و شرق شناسی، دانشگاه تهران
Autism Capital 🧩 @AutismCapital
273K Followers 0 Following Citizen journalism with a humorous flair. Following Fintech, Crypto, AI, Longevity, and wherever big grift energy goes.
(4/4) Our work paves way for more meaningful image reconstruction bounds and expands our toolkit to safely deploy novel imaging systems and algorithms IRL 🤩. Lots of opportunities to evaluate image quality for other applications like diagnosis. Code: github.com/matthewyccheun…
(3/4) Our method is nothing without meaningful application. Thx to @LaurenceECourt @nethertonians , we demonstrate our method for radiotherapy planning w/ RPA (FDA-cleared) using sparse-view CT. RPA improves planning access for low-middle income countries! rpa.mdanderson.org
(2/4) We calibrate on downstream metrics to retrieve upper/lower bound reconstructions and statistical inliers/outliers. Our reconstructions are now 1) meaningful IRL and 2) guided by statistical guarantees to contain ground truth. Thanks to the power of #conformalprediction!
How can we ensure image reconstructions are trustworthy? One way is to provide upper/lower bounds. We propose a principled way to attain reconstruction bounds based on statistical guarantees of downstream metrics. w/ @nethertonians @LaurenceECourt arxiv.org/abs/2404.15274 🧵1/4
'Metric-guided Image Reconstruction Bounds via Conformal Prediction' complete with Python code repo. 'Recent advancements in machine learning have led to novel imaging systems and algorithms that address ill-posed problems. Assessing their trustworthiness and understanding how…
5/N From the algorithmic aspect: KANs and MLPs are dual in the sense that -- MLPs have (usually fixed) activation functions on neurons, while KANs have (learnable) activation functions on weights. These 1D activation functions are parameterized as splines.
@predict_addict It obviously suck at it xdd. I agree that using it for ood is not reasonable strategy
@predict_addict Obviously - they are not working good everytime, but due to the small cost of implementing it might be easy way to inspect your dataset. So - being cautious about high uncertainty examples usually worked good for me. Being sure about confident examples is a road for a disaster
@predict_addict Entropy and BALD are often good, high precision predictors of wrongly classified examples. On many occasions, if I could inspect samples with highest entropy they were wrongly annotated cases or hard examples. Recall however is usually bad - as models tend to be overconfident.
KAN: Kolmogorov–Arnold Networks Proposes an alternative to MLP that outperforms in terms of accuracy and interpretability arxiv.org/abs/2404.19756
KAN Kolmogorov-Arnold Networks Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"),
@predict_addict what about regression tasks with KAN ?
Me encanta porque antes no entendía esas fórmulas-ecuaciones y ahora puedo leerlas sin problema.
All you need is Kolmogorov–Arnold Network! 🔥🔥🔥 complete with GitHub repo 🚀🚀🚀🚀🚀 'KAN: Kolmogorov–Arnold Networks' from @MIT and @Caltech h/t @illumattnati
18/N Computation requirements: All examples in our paper can be reproduced in less than 10 minutes on a single CPU (except for sweeping hyperparams). Admittedly, the scale of our problems are smaller than many machine learning tasks, but are typical for science-related tasks.
@tegmark 3/N Inspired by the representation theorem, we explicitly parameterize the Kolmogorov-Arnold representation with neural networks. In honor of two great late mathematicians, Andrey Kolmogorov and Vladimir Arnold, we call them Kolmogorov-Arnold Networks (KANs).
@tegmark 1/N MLPs are foundational for today's deep learning architectures. Is there an alternative route/model? We consider a simple change to MLPs: moving activation functions from nodes (neurons) to edges (weights)!
Paper: arxiv.org/abs/2404.19756 Github: github.com/KindXiaoming/p… Documentation: kindxiaoming.github.io/pykan/
This is a joint work w/ @tegmark and awesome collaborators from MIT, Northeastern, IAIFI and Caltech.
MLPs are so foundational, but are there alternatives? MLPs place activation functions on neurons, but can we instead place (learnable) activation functions on weights? Yes, we KAN! We propose Kolmogorov-Arnold Networks (KAN), which are more accurate and interpretable than MLPs.🧵
@predict_addict @MIT @Caltech @illumattnati I suggest this thread by the author x.com/zimingliu11/st…
MLPs are so foundational, but are there alternatives? MLPs place activation functions on neurons, but can we instead place (learnable) activation functions on weights? Yes, we KAN! We propose Kolmogorov-Arnold Networks (KAN), which are more accurate and interpretable than MLPs.🧵
Trends for United States
You might like
