Viewing profile — hashta

I used chatgpt's web app and I have pro subscription.

That's interesting because my experience has been almost the opposite. A few months ago I tested Gemini on converting screenshots of tables from PDF files into CSV. I tried it on s…

I think a lot of deep learning is compositional generalization. Models learn reusable pieces (abstractions, styles, procedures, constraints, etc) and recombine them in ways that ma…

I think I trained models with #params >> #training examples for hundreds of epochs, but still don't recall seeing that loss curve on real data. Curious if others have seen it with …

Interesting read. I remember the grokking paper when it came out but I don't think I've ever seen that classic grokking loss curve in my own hands on real data. Curious if others h…

this also addresses something else ... apple to some users "are you leaving for android because of their ai assistant? don’t leave we are bringing it to iphone"

I’m a long time Android user and almost switched to iPhone last year. Mostly because I use macOS and wanted better integration and also wanted to try it. Another big factor was the…

It’s literally called "SimpleFold". But that’s not really my point, from your earlier comment (".. go through all the complexities first to find the generalized and simpler formula…

To people outside the field, the title/abstract can make it sound like folding is just inherently simple now, but this model wouldn’t exist without the large synthetic dataset prod…

I’m not sure AF3’s performance would hold up if it hadn’t been trained on data from AF2 which itself bakes in a lot of inductive bias like equivariance

One caveat that’s easy to miss: the "simple" model here didn’t just learn folding from raw experimental structures. Most of its training data comes from AlphaFold-style predictions…

An effective way that usually increases accuracy is to use an ensemble of capable models that are trained independently (e.g., gemini, gpt-4o, qwen). If >x% of them have the same o…

To both questions above, just simple averaging of the logits (classification) or raw outputs (regressions) usually works well. If I had to guess why people don't use this approach …

I have a lot of experience working with both families of models. If you use an ensemble of 10 NNs, they outperform well-optimized tree-based models such as XGBoost & RFs.