Here at #Neurips2024 ! Presenting our work:
RTify: Aligning Deep Neural Networks with Human Behavioral Decisions. Please reach out if you want to learn more !

Thanks for fixing 😃

🌟 New Research Alert! 🌟
Excited to share our latest work (accepted to NeurIPS2024) on understanding working memory in multi-task RNN models using naturalistic stimuli!: with @takuito.bsky.social and @bashivan.bsky.social
#tweeprint below:

My lab has been working on comparing neural representations for the past few years - methods like RSA, CKA, CCA, Procrustes distance

We are often asked: What do these things tell us about the system's function? How do they relate to decoding?

Our new paper has some answers arxiv.org/abs/2411.08197

An image showing how three model top concept look like to classify st bernard, resnet use head and fur, while detr also use paws (maybe it help him delimitate the boundary). Clip use the head of the st bernard, but oodly the head seems to also react to human head...

A fun thesis experiment: ResNet, DETR, and CLIP tackle Saint-Bernards. 🐶
ResNet focused on **fur** patterns, DETR too but also use **paws** (possibly because it helps define bounding boxes), and CLIP **head** concept oddly included human heads — language shaping learned concepts?

Neuronal sequences in population bursts encode information in human cortex - Nature The temporal order of neuronal firing within bursts of population spiking in the human anterior temporal lobe is dependent on the category as well as the identity of the individual stimulus, and this ...

This study shows that spike sequences carry information beyond what rates and latency to first spike do:

www.nature.com/articles/s41...

My reactions:

1) Cool to see this in humans.
2) Are people still surprised that spike times carry information beyond rates/first-spike latency?!?!?!

🧠📈 🧪

FourCastNet – Janelia CVML Weather forecasting with Adaptive Fourier Neural Operators

We've been holding a weekly Computer Vision & Machine Learning reading group at Janelia since 2014, and we started a blog about some of the papers we're reading and recommend. Here's our first post about FourCastNet, an ML algorithm for weather forecasting
janelia-cvml.github.io/blog/posts/F...

My favorite slides -- as someone doing ML with an academic lab, it is pretty mind-boggling how huge spending is. It puts HHMI's $500M / 10 years commitment to AI funding in perspective...