Blending genomics with deep learning, making GPU-accelerated computers do complicated stuff without giving them any food or water.
Canberra
Joined July 2018
- Tweets905
- Following217
- Followers377
- Likes612
Exciting news! Whether it's Donald Trump Jr. or a pair of his father’s socks (one for President and one for Vice President), they could run in 2028 and once again win both the electoral and popular votes! Amazing!
Eli Niktab retweeted
>renames it to the Department of War
>names himself the Secretary of War
>fights one war
>loses
Somebody shut this pathetic MEK puppet up. This scripted propaganda is beyond tired, and @Maryam_Rajavi isn’t exactly at an age to swap husbands again or do threesomes with dogs anymore!
What Reza Pahlavi is attempting to do—by declaring himself Iran's "transitional leader"—is dangerous and will only destabilize the situation further.
Pahlavi has next to no support inside the country, as he is literally the son of the man who was overthrown by the Iranian people after years of brutality, theft and oppressive rule.
The Iranian people will not resort back to a tyrannical monarchy after freeing themselves of a tyrannical Islamic regime.
This would be a formula for disaster.
Eli Niktab retweeted
Changing training data alone can improve deep learning prediction of spatial transcriptomics gene expression from histology images by 38% (without any changes to model architecture).
We've updated our preprint showing this with expanded results: biorxiv.org/content/10.1101/…
🧵👇 1/4
I would have shared the picture of my locked and secured brand-new bike with you if it hadn't been stolen after just ONE day from the campus! #campussafety @ourANU
Eli Niktab retweeted
Did you know that networks trained with different learning rates extract different features (and a different number of them!) from the data? Come by our poster at HiLD Workshop #ICML2024 tomorrow to discuss it with @irsadrtdinov!
Paper: openreview.net/forum?id=IID2…
1/6
Eli Niktab retweeted
A student told me, "I don't get the difference between model fitting by:
1. minimum Mean Square Error (MSE) and
2. Maximum Likelihood Estimation (MLE)"
To help this student, I built out this #Python @matplotlib dashboard for fitting a Gaussian parametric distribution to data while calculating & visualizing the training data MSE and likelihood!
Many students have found this helpful, so I shared it on #GitHub @ github.com/GeostatsGuy/DataS… ∀. #DataScience
Eli Niktab retweeted
finally finished the antibody ML primer post
if you are in the protein ML field, not in antibody ML, and would like to understand antibody ML bit more, you’re my ideal audience!
abhishaike.com/2024/04/15/a-…
🧵 🧵 🧵 – at Queens, NY
Prepare for the onslaught of OpenAI's Sora-related posts, or consider avoiding your LinkedIn feed for a bit! I think I will fully embrace my millennial side and stick to Instagram for a bit with my less tech-focused friends, who only share harmless cat videos. #sora
We researchers are not software developers, so I’m not a big fan of learning obscure syntax only to avoid boilerplate code (exactly why I don’t like C++ as opposed to C) …
but they're so much new syntax added to Python after version 3.6 that you can no longer read new codes without knowing the new stuff. I wish Python had remained an academic language instead of becoming widely adopted for production
realpython.com/python-data-c…
Eli Niktab retweeted
Eigenvalues of random matrices with iid entries converge to the Wigner circle law. This is universal (does not depend on the law of the entries), as proved by Tao and Vu in 2010. For Gaussian matrices, this defines a determinental point process. en.wikipedia.org/wiki/Circul…