DJ @DuaneJRich
Helping companies do machine learning stuff. https://t.co/JOG4SBUqYn YouTube channel: https://t.co/0f67ttsk59 truetheta.io San Francisco, CA Joined April 2014-
Tweets983
-
Followers5K
-
Following843
-
Likes2K
I'm working on a retail recommender system and thinking first about evaluation. Beware: • Evaluating a candidate RS by seeing how well it predicts test set item purchases isn't quite what you want, since all items purchased are under the existing RS. The data depends on the RS…
New paper surveying multimodal LLM hallucinations: arxiv.org/abs/2404.18930 It creates a taxonomy of the varied ways hallucinations appear, with an intent to reveal causes and explain mitigation strategies. It's an educational read and an admirable effort. Hallucinations,…
Today I was refreshing on recommender systems when I came across this nice retrospective on what's worked at Amazon. amazon.science/publications/t… I'm posting about it because I'm impressed with how simple the original idea is. For a given pair of items in the inventory, they compute…
After tuning prompts manually and reluctantly, it's nice to see this prompt optimization package from Microsoft. github.com/microsoft/sammo You give it something that measures prompt performance (you know, the hard part), a way of generating many variations of a prompt, and it…
Ha! Speak of the devil - I just purchased this beast. Haven't read a page. One day..
Ha! Speak of the devil - I just purchased this beast. Haven't read a page. One day.. https://t.co/XMEHxoA0cQ
The Kaplan–Meier estimator, an assumption-light means of estimating survival curves: It became part of standard practice for analyzing medical clinical trials. And so, the paper introducing it is one of the most cited papers in statistics. As far as stats contributions go..…
The Kaplan–Meier estimator, an assumption-light means of estimating survival curves: It became part of standard practice for analyzing medical clinical trials. And so, the paper introducing it is one of the most cited papers in statistics. As far as stats contributions go..… https://t.co/fK5fZ9NfBO
"The gradient is the direction of steepest ascent." I remember seeing that in college thinking it was a cute fact and feeling annoyed having to memorize the proof. Turns out it connects calculus and optimization, and gives us the simple algo that trains most neural nets.
"The gradient is the direction of steepest ascent." I remember seeing that in college thinking it was a cute fact and feeling annoyed having to memorize the proof. Turns out it connects calculus and optimization, and gives us the simple algo that trains most neural nets.
Another example where the best education from a leader of the field is free. cedricvillani.org/sites/dev/file…
Another example where the best education from a leader of the field is free. cedricvillani.org/sites/dev/file…
In November, I got quietly interested in randomized Numerical Linear Algebra. But I'm not actually quiet, so here's the video: youtu.be/6htbyY3rH1w?si…
Watched this last night. It's the best explanation of back prop I've seen.
Watched this last night. It's the best explanation of back prop I've seen.
Some thoughts on gov cybersecurity: truetheta.io/concepts/opini… It's interesting.. Department of Defense spending on AI will dwarf VC spending over the next decade, and none of that is represented on X. No one there cares about social media - kind of refreshing.
Devin is quite impressive and so is the team (holy shet 10 IOI gold metals? lol wow). But there are some absolutely unhinged projections. "SWEing is a thing of the past, natural language is all you need," yada yada.. I think in 10 years, we'll see a competitive advantage for…
ChatGPT < Perplexity I've switched over to using Perplexity almost exclusively, especially for their API. Faster with internet access and has more generous rate limits. I suspect this is b/c Perplexity is less crowded, so the difference may shrink. But for now, it definitely…
Well I disagree. In 25 years, I bet many people will still be writing code. Without a truly astonishing breakthrough, LLMs will continue to represent only what's in the training data, and there will continue to be coding challenges for which the data isn't enough to determine…
Well I disagree. In 25 years, I bet many people will still be writing code. Without a truly astonishing breakthrough, LLMs will continue to represent only what's in the training data, and there will continue to be coding challenges for which the data isn't enough to determine…
Richard McElreath �.. @rlmcelreath
46K Followers 2K Following Anthropologist @MPI_EVA_Leipzig - telling anyone who will listen that, if we are very careful and try very hard, we might not completely mislead ourselvesChris Albon @chrisalbon
86K Followers 2K Following Director of Machine Learning at the Wikimedia Foundation. We host Wikipedia.Steven Brunton @eigensteve
45K Followers 1K Following Teaches math to engineers: https://t.co/TJ5i3Pg678 Professor @UW researching #MachineLearning for #Dynamics and #Control, especially for #FluidDynamics.Sean J. Taylor @seanjtaylor
46K Followers 4K Following Building @MotifAnalytics. Formerly @Lyft and @Facebook. Keywords: Experiments, Causal Inference, Statistics, Machine Learning, Economics.Valeriy M., PhD, MBA,.. @predict_addict
17K Followers 3K Following PhD in machine learning | conformal prediction | time-series | author of bestselling Practical Guide to Applied Conformal-Prediction https://t.co/ugR9TtXd29Hamel Husain @HamelHusain
23K Followers 2K Following Researcher focusing on LLMs: https://t.co/iVZDFdIQiE Previously, dev tools and infra for ML. Ex @Github, @Airbnb, @DataRobot. @fastdotai core contributor.Benjamin Vincent, DPh.. @inferencelab
3K Followers 940 Following Data Scientist | Bayes | Causal reasoning | Python + Julia | Ex-academic | #MMT. Part of @pymc_labsSam Power @sp_monte_carlo
17K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. (he / him)DJ @djstrangeloop
107 Followers 5K Followinghruday mallick @bapicute
55 Followers 1K FollowingYusuke Abe @AbeYusuke3
442 Followers 6K Following searching for new ideas on how to solve the unanswered questions for all mankind humanity freedom sci/tech/med #rust #quantum #AI intp-ubr-mensa-2e ∞ for ∞Chipmunk @AlvinMesser
87 Followers 843 FollowingGnewtonTheGnu @GnewtonG36443
58 Followers 565 FollowingEduardo @eduardomelgg
11 Followers 420 Followingdj Crystal @Crystal_ine1
0 Followers 14 Following Dj/influencer connect with me on instagram _Crystal_inePetr Hornicky @PetrHornicky
150 Followers 757 Following Shared opinions are my own. References to the disruption leading companies are for education & entertainment purposes. For everything else do your own research.Xeligbar @xeligbar
54 Followers 64 Followinglengchai6 @antoto81
453 Followers 3K FollowingCatarina Schrandt @CatarinaSc65383
30 Followers 5K FollowingZhaoyang Wang @wangwan83764204
326 Followers 4K Following CS PhD student at Uni of Birmingham in the United Kingdom. Research interests: Automated Machine Learning, Online Learning, and Reinforcement Learning 🏳️🌈Noreen Mcfadden @noreen_mcfadden
60 Followers 980 Following Thank you for reading. I had a career with Royal Mail, driving a van for 13 short years, which were filled with adventure and laughter, with friends I miss🥰dj tomsten @TomstenDj
145 Followers 727 Following Dj tomsten is an experimental artist on spotify. Melodic techno and electronic techno is his passion. 69 robot tom is a dj and a music producer from swedenCamila Chisholm @CamilaC34042
113 Followers 5K FollowingJason Cox @JasonOfficialMe
362 Followers 4K Following 🌐📉 | Data Engineer @Blizzard_Ent | Network Science Instructional Associate @gtcomputing | My posts sometimes represent myself but never my employer.Eta Car @etacar
74 Followers 760 Followingssteevens @Steevens43
164 Followers 5K FollowingTomoko Bruss @TomokoB8216
84 Followers 5K FollowingMr. Jenkins @IAmMrJenkins
60 Followers 639 FollowingMarcos @MAMware
90 Followers 510 FollowingJeremy Lewi @jeremylewi
757 Followers 265 Following ML platform engineer. Applying AI to devops; https://t.co/bQezVVwxFC Ex @primer_ai, @GoogleWilson Hu @nanweihu
120 Followers 2K FollowingPaine @thomaspainecn
8 Followers 122 FollowingVictor Hah @VictorHah
130 Followers 464 Following Banker turned entrepreneurㅣ@Columbia_Biz, @HarvardBizAn, @MITProfessional alumㅣ@DeepLearningAI MentorDavida Terris @DTerris68561
67 Followers 5K FollowingBatman.jedi @Batmanjedi90
85 Followers 409 Followingd45d @mtv4566
290 Followers 4K FollowingAdam J @Adamwxp
31 Followers 517 FollowingBen Charoenwong @BenCharoenwong
1K Followers 2K Following Finance prof @NUSBizSchool. @ChicagoBooth and @UMich alum. I mostly RT news and make snide remarks. he/him.Shayan Riyaz @ShayanRiyaz
84 Followers 47 Followingandrew ilachinski @AI_ilachinski
806 Followers 3K Following I straddle two worlds: one grounded in science (complexity/AI), the other, in art (photography). This page is focused on the more scientific pursuits.Carlos Alberto Haro @haro_ca_
2K Followers 2K Following 🇲🇽 I f*cking love data. Started doing stats, got lost, and somehow ended up mixing data/ML/software engineering for food.finsoy @finsoyapp
50 Followers 94 Following Load up on finance beans, identify opportunities to invest and trade.wirip @nstableInfusion
240 Followers 4K Followinggeeksguide @geeksguidenet
163 Followers 2K FollowingAutonomy Circle @autonomycircle
1K Followers 714 Following Welcome to Autonomy Circle: A hub for robotics and control systems enthusiasts 🦾 Join to learn, collaborate, and advance the field 👩💻🧑💻Toni Sien @sien_toni96662
91 Followers 5K FollowingAndrej Karpathy @karpathy
980K Followers 905 Following 🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥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.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.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/q2Qoey80GxGrant Sanderson @3blue1brown
365K Followers 362 Following Pi creature caretaker. Contact/faq: https://t.co/brZwdQfdifAlfredo Canziani @alfcnz
86K Followers 268 Following Musician, math lover, cook, dancer, 🏳️🌈, and an ass prof of Computer Science at New York UniversityAndrew Ng @AndrewYNg
1.0M Followers 914 Following Co-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCsKevin Patrick Murphy @sirbayes
42K Followers 334 Following Research Scientist at Google Brain / Deepmind. Interested in Bayesian Machine Learning.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.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.Gabriel Peyré @gabrielpeyre
92K Followers 449 Following @CNRS researcher at @ENS_ULM. One tweet a day on computational mathematics.MIT CSAIL @MIT_CSAIL
298K Followers 22K Following MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL). Media Inquiries: [email protected]Richard McElreath �.. @rlmcelreath
46K Followers 2K Following Anthropologist @MPI_EVA_Leipzig - telling anyone who will listen that, if we are very careful and try very hard, we might not completely mislead ourselvesMatt Henderson @matthen2
79K Followers 2K Following maths, visualisations, conversational AI. currently @RekaAILabs - previously: @Apple AI/ML, @PolyAI, @GoogleAI, MSc @EdinburghUni, PhD @Cambridge_EngChris Albon @chrisalbon
86K Followers 2K Following Director of Machine Learning at the Wikimedia Foundation. We host Wikipedia.Frank Nielsen @FrnkNlsn
23K Followers 1K Following Machine Learning & AI, Information Sciences & Information Geometry, Distances & Statistical models, HPC. "Geometry defines the architecture of spaces" @SonyCSLJean de Nyandwi @Jeande_d
38K Followers 775 Following Deep Learning, Vision 🤍 Language, Multimodal LLMs • AI Education • CMU Research blog: https://t.co/1BEFLZAqe7 ML Pack: https://t.co/7PkTyDvurijack morris @jxmnop
11K Followers 768 Following getting my phd in nlp @cornell_tech 🚠 // academic optimist // tweeting from the snack aisle at trader joesYen-Huan Li @yenhuan_li
2K Followers 536 Following Associate professor in CS @ National Taiwan University. PhD in CS from EPFL. Learning, optimization, statistics, and some quantum information.Jonathan Whitaker @johnowhitaker
7K Followers 957 Following Data scientist and AI researcher. R&D at https://t.co/9xrxRrGfEE.wallingf @wallingf
1K Followers 197 Following I'm a CS professor at a medium-sized public university, interested in most things about programs, and most other things, too. @[email protected]Carmen Gutierrez @carmguti
7K Followers 1K Following founding @ResiduaAI, prev ms cs @StanfordEng, physics @stanfordJeremy Lewi @jeremylewi
757 Followers 265 Following ML platform engineer. Applying AI to devops; https://t.co/bQezVVwxFC Ex @primer_ai, @GoogleGreg Linden @greglinden
3K Followers 183 Following an internet relic, on mastodon @[email protected], glinden on blueskyBobak Moallemi @BobakDigital
178 Followers 2K Following Economist & Data Scientist / Prev. @Opendoor, @Lyft, @LinkedIn, @FederalReserve / PhD @StanfordGSBNan Jiang @nanjiang_cs
7K Followers 72 Following machine learning researcher, with focus on reinforcement learning. asst prof @ uiuc cs. Course on RL theory (w/ videos): https://t.co/vqVKwY4RJEGreg Kamradt @GregKamradt
25K Followers 722 Following Building AI + B2B products 🖥️ Content: https://t.co/kLERwNtzqi Feedback is great: https://t.co/A6mrmjCem5 Prev. @digits @salesforceSmarter Every Day @smartereveryday
373K Followers 1K Following Hello, I'm Destin. I'm an Engineer with a YouTube channel called "Smarter Every Day".Ben (e/sqlite) @andersonbcdefg
3K Followers 3K Following 🤖 Computer scientist, next-word-prediction enjoyer 📊 Prev. research fellow @ Stanford RegLab 🛠️ bUiLdiNg sOmeThiNg nEw (https://t.co/mdYPZmjSzN - YC S23) 🏳️🌈Yuke Zhu @yukez
15K Followers 464 Following Assistant Professor @UTCompSci | Co-Leading GEAR @NVIDIAAI | CS PhD @Stanford | Building generalist robot autonomy in the wild | Opinions are my ownCharles Qi @charles_rqi
7K Followers 220 Following Autopilot and AI @Tesla | Prev: Research Scientist & Manager @Waymo | Postdoc @FAIR, PhD @Stanford | COO at the Lighthouse Mentorship Program.Palmer Luckey @PalmerLuckey
219K Followers 2K Following I am a technology enthusiast, writer, and modder. Founder of ModRetro, @Oculus VR, and @Anduriltech. Keeping American superheroes safe with autonomous systems.Aleix M. Martinez @AleixMMartinez
1K Followers 395 Following Sr. Principal Scientist and Director of a Science @amazon, Professor @OhioState. Opinions my own 👉 hiringLucas Beyer (bl16) @giffmana
56K Followers 446 Following Researcher (Google DeepMind/Brain in Zürich, ex-RWTH Aachen), Gamer, Hacker, Belgian. Mostly gave up trying mastodon as [email protected]Henry Mao @Calclavia
4K Followers 412 Following CTO @ https://t.co/PrvwcJieE7 ($5M+ ARR) Building AI to supercharge your research. Sharing thoughts on startups & machine learning.finbarr @finbarrtimbers
8K Followers 647 Following large models @midjourney. ai hot takes at https://t.co/pSeuTpK0xO.Yangqing Jia @jiayq
12K Followers 263 Following Founder @leptonai. @UCBerkeley alumni. ex @google & @facebook. ex vp @AlibabaGroup. Open source work on caffe, @pytorch, @tensorflow, & @onnxai.TechWorld with Nana |.. @Njuchi_
38K Followers 178 Following Helping people break into DevOps (900K+ Community) 🚀 | Docker Captain 🐳 | AWS Containers Hero ☁️ | CNCF AmbassadorErik Meijer @headinthebox
27K Followers 0 FollowingTrenton Bricken @TrentonBricken
7K Followers 2K Following Trying to figure out what makes minds and machines go "Beep Bop!" @AnthropicAIYusuf Mehdi @yusuf_i_mehdi
30K Followers 153 Following EVP and Consumer CMO. Empowering people to harness AI to live better.Marc Andreessen 🇺�.. @pmarca
1.4M Followers 24K Following Techno-optimist. E/acc. Technology brother. Move Fast and Make Things. p(Doom) = 0; p(“1984”) = not 0.Dwarkesh Patel @dwarkesh_sp
55K Followers 700 Following Being pretrained Host of Dwarkesh Podcast https://t.co/3SXlu7fy6N https://t.co/rEhnfYywXY https://t.co/hQfIWdM1UnNathan Lambert @natolambert
25K Followers 690 Following Figuring out AI @allen_ai, "rl boi" DM me papers. Writes @interconnectsai, talks @retortai Has phd and some credentialsShengwu Li @ShengwuLi
35K Followers 760 Following Economist. @Harvard. Mechanism design, behavioral theory.Christian Caballero @ccaballeroh10
285 Followers 251 Following Computer Science doctoral student / Causal Inference / NLP / Computational Linguistics / AI / Machine Learning / Former spacecraft engineer and astrodynamicistAndriy Burkov @burkov
19K Followers 142 Following Author of 📖 The Hundred-Page Machine Learning Book and the 📖 Machine Learning Engineering bookBilly Pope @BillyPope23
273 Followers 296 Following Cyber Ops Professional, Harvard alum, and SAASS PhD candidate. Tweeting my views; not those of the DoD.Matei Zaharia @matei_zaharia
39K Followers 1K Following CTO at @Databricks and CS prof at @UCBerkeley. Working on data+AI, including @ApacheSpark, @DeltaLakeOSS, @MLflow, https://t.co/94gROE5Xa0. https://t.co/nmRYAKG0LZMichael Littman @mlittmancs
8K Followers 160 FollowingElia Kaufmann @kaufmann_elia
263 Followers 55 Following PhD Student at the Robotics and Perception GroupMike Pound @_mikepound
16K Followers 138 Following Lecturer and researcher in Computer Science at Nottingham University. Also appear on Computerphile from time to time.tom cunningham @testingham
1K Followers 2K Following @openai. Ex Otago, LSE, Harvard, Tel Aviv, IIES Stockholm, Facebook, twitter, integrity institute.Mattias Villani @matvil
2K Followers 788 Following Big fan of Bayes, @julialanguage and @sscnapoli. Stats professor @stockholm_uni.Tri Dao @tri_dao
19K Followers 365 Following Incoming Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.Computerphile @computer_phile
45K Followers 30 Following YouTube videos about computers and the internet and stuff... Sister project to @numberphileSt. Ratej @stratejake
3K Followers 649 Following Techno-Optimist. Research Engineer @GoogleARVR (x @oculus/@realitylabs). Physics, EE, Neuro, ML, HCI. Opinions are my own.akshay Balsubramani @_bakshay
801 Followers 663 Following 💻ML/AI |🧬🧪| 📈 • @sanofi, @ThirdRockV • @StanfordMed, @UCSD, @MSFTResearch, @GoogleAI &c • 🇸🇬🇺🇸🇮🇳 • Caveat: humorSignal Processing @DSP_fact
32K Followers 18 Following Digital signal processing, acoustics, Fourier analysis, etc.Ethan Epperly @ethanepperly
1K Followers 470 Following PhD candidate in applied math @Caltech and @doecsgf fellow interested in computational linear algebra he/himAfter 25 years of working in the ML space I agree that many early stage companies (Series A-ish and earlier) shouldn’t be hiring MLEs However I think companies need a fractional MLE (.05) to help ensure the foundations get built properly for MLEs later on. Data Eng,…
🆕 the one and only @jxnlco on: • Why Pydantic is -still- All You Need • Why most AI frameworks aren't VC backable • Why you'd be happier being bootstrapped • Why you should NOT hire ML Engineers • the definitive origin of Instructor latent.space/p/instructor (and bonus…
Jeremy is THE most talented infra/devops person I know. He’s created a specialized IDE + Copilot for DevOps : K8s, Cloud, etc - based on notebooks! It’s open source, accompanied by a blog that shows his thinking 👇
I'm experimenting with implicitly collecting human feedback to improve an AI for devops. I see lots of people opting for shiny, new observability tools. Here’s a post extolling the merits of reusing your existing logging infrastructure. foyle.io/docs/blog/logf…
The vector field of a diffusion model has some interesting properties. Early on samples are mostly noise, so the model's best guess is to predict the mean. Later on the model has more information and the vector field starts to reveal the local structure of the distribution.
I've spent the past ~2 weeks building a GPU from scratch with no prior experience. It was way harder than I expected. Progress tracker in thread (coolest stuff at the end)👇
@ajwchin and I are pre-training *a lot* of Transformers and State Space models lately (from scratch) because we're building foundation models for each of our customers. More to come soon on how we're using them (and I encourage you to read our post from February if you want to…
A big reason this works so well is because @benjamin_warner has put in many *many* hours over the last few weeks on debugging and fixing complex performance issues deep inside the Transformers library. It's the kind of work that's rarely appreciated -- so let's do so now! :D
Easily Fine-tune @AIatMeta Llama 3 70B! 🦙 I am excited to share a new guide on how to fine-tune Llama 3 70B with @PyTorch FSDP, Q-Lora, and Flash Attention 2 (SDPA) using @huggingface build for consumer-size GPUs (4x 24GB). 🚀 Blog: philschmid.de/fsdp-qlora-lla… The blog covers: 👨💻…
Last 28 days 🤯 While the Zuck & Trenton/Sholto episodes are doing extremely well on YouTube, what I'm proudest of is that most of these views are actually from Sarah Paine content! She is one of the greatest living historians, but her work wasn't really publicly well known…
OK, this is probably going to raise more questions than it answers, but I just want to put this out here so that no one ever says "we can just get around the data limitations of LLMs with self-play" ever again.
I wrote about how we decompose data analysis work at @MotifAnalytics, inspired by more traditional tools for data analysis (like the @tidyverse) and adapted those steps for working with event sequence data. linkedin.com/pulse/transfor…
tagging @Google ... maybe someone is listening...
Google scholar removed our @CambridgeUP book "Data-Driven Science and Engineering" and now it points to a book review instead of the actual book. Has this happened to anyone else? Any ideas to fix this? I've contacted scholar support a couple times this month, but no help yet.
Yup that was definitely a good idea
Considering moving from Austin to SF to be able to meet more interesting people in person. People familiar with SF, good or bad idea at this point?
Implementing a Diffusion Model on a simple 2D dataset is a fun exercise. Here is a visualization of the the paths followed when sampling from a Denoising Diffusion Probabilistic Model (DDPM) trained on a simple spiral dataset.
"Yes, and" this is not a problem when we filter data. CC @datologyai et al. It's quite obvious that if we take random samples, we hit the curse of dimensionality and require exponential # of samples. If we actively select the data to train on, we shall be much more efficient
It turns out the data bottleneck problem is more dire than initially thought: AI model performance - which can be largely attributed to the presence of test concepts within their vast pretraining datasets - increases linearly with exponentially more data. RIP: Scaling laws
@dvassallo unethical? It's a turd, we should call a turd a turd. We should be grateful that we have YouTubers powerful enough to tell the truth without being sponsored to lie like everyone else
Solving linear systems comes in different flavors. en.wikipedia.org/wiki/Least_squ…
I assume the purpose of the focus on "ML for social impact" is to get URMs interested in the field (it would be good to hear from the NeurIPS people who created this...), but I think in reality this track will be used by already high-achieving students (not URMs) to further pad…
Hmm. The longer I look the weirder this call. I have worked with curious high-schoolers for 3 years now but I can't think of anyone for whom this is relevant. The focus on "ML for social impact" is prescriptive and narrow, plus it smells like mainly virtue signaling.
Now that I've implemented a super basic #transformer (self-attention etc..), can someone recommend articles/blogposts describing useful tricks of the trade? Eg. improved training efficiency/stability, sub-quadratic attention, implementation tricks, architecture tweaks, etc.. #AI
Someone wanted me to join the two co-founders' startup as the first backend engineer, for 0.30-0.70% of equity I politely declined, then he asked me to recommend someone — dude, why the hell would I recommend someone I value to carry your whole operation for 0.3% ownership
Our new youTube channel: youtube.com/playlist?list=… Comments welcome!
With a new tabular deep learning method trending, let me stress that most studies do not investigate realistic settings (≠ huge tables) with strong baselines. 99% of the cases gradient boosting (as XGBoost) is much more robust, faster, and usable. This matters long term.