←
Huth Lab9 posts
Huth Lab avatar

Huth Lab

@HuthLab

computational & experimental neuroscience/CS lab at UC Berkeley. fMRI + language + machine learning. Looking for students and postdocs! PI: @alex_ander

◷ Joined December 2016
Shailee Jain avatar
⟳ Huth Lab retweeted
Shailee Jain@shaileeejain·24 Aug 2023

Our ✨Large-scale fMRI dataset on naturalistic language✨is now out in Nature Scientific Data! MANY hours (5 to 16 per indiv) on MANY ppl (8 indiv)! We also included code to fit encoding models exactly like all @HuthLab papers! Pls read @alex_ander's awesome thread on... 1/2

Our big language fMRI dataset is now officially published! 📰 The paper: nature.com/articles/s41597-0… (free pdf: nature.com/articles/s41597-0…) 🧰 Code to download data & build models: github.com/HuthLab/deep-fMRI… 💾 The dataset: openneuro.org/datasets/ds003…

Jerry Tang avatar
⟳ Huth Lab retweeted
Jerry Tang@jerryptang·1 May 2023

Our language decoding paper (@AmandaLeBel3 @shaileeejain @alex_ander) is out! We found that it is possible to use functional MRI scans to predict the words that a user was hearing or imagining when the scans were collected nature.com/articles/s41593-0…

Richard Antonello avatar
⟳ Huth Lab retweeted
Richard Antonello@NeuroRJ·4 Nov 2022

Why are language models so great at encoding brain responses to natural language? In our new paper (https://t.co/V8Gil16otn), we explore two new correlates of encoding performance and their implications on cognitive theories of language processing. (1/12)

1:35
Jerry Tang avatar
⟳ Huth Lab retweeted
Jerry Tang@jerryptang·30 Sep 2022

very excited to share our paper on reconstructing language from non-invasive brain recordings! we introduce a decoder that takes in fMRI recordings and generates continuous language descriptions of perceived speech, imagined speech, and possibly much more biorxiv.org/content/10.1101/…

Amanda LeBel avatar
⟳ Huth Lab retweeted
Amanda LeBel@AmandaLeBel3·24 Sep 2022

New Dataset Alert! I'm very happy to official announce a naturalistic language fMRI dataset now available! This dataset includes 8 participants listening to 5 hours each of the moth radio hour. biorxiv.org/content/10.1101/…