Hot-off-the-press! The latest paper from #HiRO is now available online JAMA Cardiology

Deep Learning–Augmented ECG Analysis for Screening and Genotype Prediction of Congenital Long QT Syndrome River Jiang

jamanetwork.com/journals/jamac…

#cardiogen #EPeeps #LQTS UBC Medicine ICMtl

How to use OpenAI's ChatGPT for creative writing collaboration.

#OpenAI #ChatGPT

andrewmayneblog.wordpress.com/2022/11/30/col…

I'm speechless.

Not peer-reviewed yet but a submitted paper.

The 'presented images' were shown to a group of humans. The 'reconstructed images' were the result of an fMRI output to Stable Diffusion.

In other words, #stablediffusion literally read people's minds.

Source 👇

Vision Transformers (ViTs) are a powerful deep learning architecture, but what’s the difference between ViT and a text-based transformer like BERT? Despite being applied in completely different domains, these models have only one major difference… 🧵[1/7]

$2 per million tokens 🤯

Medlife Crisis (Rohin) Oh great just what cardiologists need, more ventricles

Remember that paper that just has the letter T for error bars?

Well it got retracted.

Notice of retraction: “readers have raised concerns that the error bars in Figure 9 appear to be the letter ‘T’”

🤷 sometimes the system works
retractionwatch.com/2022/12/22/tha…

Transformers are all the rage today. But neither DALLE nor Stable Diffusion uses Transformer for image generation. Instead, they rely on a 7-year-old, Jurassic-era neural architecture. Why? 🤷🏾‍♀️⁉️ It’s finally time for Transformer and Diffusion to join forces! Quick 🧵👇:

openAI or 'open'AI?

1/ OpenAI's #chatgpt release will mark the beginning of the end of the golden age of open research in deep learning.

This will have significant implications for LLM research going forward.

Here are some thoughts from me, Vivek Raghunathan and Rajhans Samdani 🧵