Sunanda Gamage
@gamage_sunanda
Followers
212
Following
1K
Media
0
Statuses
38
PhD candidate at Western University. Interpretable machine learning.
London, Ontario
Joined July 2019
Have you ever wanted to train LLMs in pure C without 245MB of PyTorch and 107MB of cPython? No? Well now you can! With llm.c: https://t.co/w2wkY0Ho5m To start, implements GPT-2 training on CPU/fp32 in only ~1,000 lines of clean code. It compiles and runs instantly, and exactly
github.com
LLM training in simple, raw C/CUDA. Contribute to karpathy/llm.c development by creating an account on GitHub.
286
2K
13K
Our preprint on OpenFold, our trainable reproduction of AlphaFold2, is finally up ( https://t.co/3EoTzE3Xdb)! Since we open-sourced parameters in June, we've trained the model to high accuracy more than 50 times, on a variety of datasets. Here's what we learned (a lot) -> (1/19)
15
223
937
A treasure trove for software engineers.
it's the end of the year and some people have education budgets to spend. What tech books have really helped you?
0
0
1
It's great to see this kind of top notch work in the natural sciences being fully open source. I hope this becomes the norm.
Last year we presented #AlphaFold v2 which predicts 3D structures of proteins down to atomic accuracy. Today we’re proud to share the methods in @Nature w/open source code. Excited to see the research this enables. More very soon! https://t.co/6uiV51Xly5
https://t.co/CLo7EKubBT
0
1
3
applied-ml curated papers, articles, and blogs on data science & machine learning in production. @eugeneyan
https://t.co/v7Y6jVw5yI
github.com
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production. - eugeneyan/applied-ml
1
117
478
If you have less than 3 hours to spare & want to learn (almost) everything about state-of-the-art explainable ML, this thread is for you! Below, I am sharing info about 4 of our recent tutorials on explainability presented at NeurIPS, AAAI, FAccT, and CHIL conferences. [1/n]
32
848
4K
With EigenGame, our team formulated PCA as a competitive multi-agent game, testing a new approach to an old problem. @iclr_conf they shared new insights & algorithms that scale to massive data sets & offer an alternative to explore fundamental ML problems:
6
99
435
A little over 12 years ago, the police started building a case against me. That was stressful. They were watching. They wanted to take me off the streets. Here is the story of how I fled Cuba and came to the United States. ↓
91
230
2K
If you’ve been fortunate enough to do well this year, consider joining me and @VitalikButerin by donating at the addresses below. But if all you have is Twitter, help spread the word. For every RT, I’ll donate another $50 to fight COVID in India, up to $100k. #cryptovscovid
With the efforts of @balajis we are trying to increase the reach of this fund Eth Address to donate: 0x68A99f89E475a078645f4BAC491360aFe255Dff1 BTC : bc1q220k2449fau0pxu9hfn28q3w4k99ep9hwsa5fa DOGE : D6fWVp613N3dyLM6Zoghj3dZaEjbGZ8gpX Tron : TSZMcrQzMLdKrgiMPoe2uQMHLeEpkf2j8E
533
9K
7K
A great read for machine learning and statistics folks.
With postdoc Stephen Bates and Trevor Hastie, I have just completed a new paper "Cross-validation: what does it estimate and how well does it do it?"
0
0
1
Are you an undergraduate student in Sri Lanka interested in pursuing graduate studies abroad? @goasksef is offering a 6-month mentorship program with individuals in STEM from all around the world 🌎 ‼️Deadline March 14! ‼️
Join the ScholarX batch of 2021! Apply now! ScholarX is a 6-month program for Sri-Lankan undergraduates who would like to get free premium mentoring during their study period.
0
3
11
A great thread on differences between scientific fields and why there is no one scientific method.
I've worked in a lot of different sciences and what I've discovered is that each science is its own slightly bizarre alternate reality where the scientific method turned out differently.
0
1
0
There are a lot of things we can learn from this pandemic about personal and public health, and I hope we carry them over to post pandemic life.
I’ll never forget doing compressions in a young child who was slowly dying from Influenza B, his heart being the last organ to fail. He made it (🤲🏽❤️), which speaks to his absolute tenacity. Look at flu deaths in kids this yr. It’s remarkable. 👀 I hope we can learn from this.
0
0
0
A good thread on applications of graph neural networks
What's the coolest/clearest application of graph neural networks?
0
0
1
Thrilled to announce our first major breakthrough in applying AI to a grand challenge in science. #AlphaFold has been validated as a solution to the ‘protein folding problem’ & we hope it will have a big impact on disease understanding and drug discovery:
151
2K
8K
I am recruiting PhD students for Fall 2021 @IllinoisCS. If you are interested in working in Compilers, ML for Systems, Program Analysis, High Performance DSLs consider applying to our graduate program and get in touch with me. Retweets are appreciated.
9
151
285
A good intuitive explanation of the double descent phenomenon.
The Bias-Variance Trade-Off & "DOUBLE DESCENT" 🧵 Remember the bias-variance trade-off? It says that models perform well for an "intermediate level of flexibility". You've seen the picture of the U-shape test error curve. We try to hit the "sweet spot" of flexibility. 1/🧵
0
0
3
Are you a student, researcher or just curious about the world of artificial intelligence? We’ve created a learning resources page to help people at different stages of their learning journey find out more about the field of AI. https://t.co/FsUv7GIw1a
12
429
1K
The SICP lectures are definitely worth watching for anyone in computer science and the SICP book is a great read too.
0
0
0
AS A STATISTICIAN, I think our obsession with objective truth and individualism is making us less effective at fighting the pandemic. There's been a lot of debate recently about whether covid-19 is airborne. It's the wrong question! Let me explain...
8
179
560