Joel Ye
@joelye.bsky.social
NeuroAI PhD student @ Carnegie Mellon. Being a brain-computer interface.
What it is:
- NDT3 is "just" an autoregressive Transformer, for decoding behavior from neural spiking activity
- We tokenize behavior timeseries by splitting and neural data by patching (a la NDT2/ViT). Thus, the model can ingest most motor brain-computer interface datasets
- NDT3 is "just" an autoregressive Transformer, for decoding behavior from neural spiking activity
- We tokenize behavior timeseries by splitting and neural data by patching (a la NDT2/ViT). Thus, the model can ingest most motor brain-computer interface datasets
February 7, 2025 at 2:21 PM
What it is:
- NDT3 is "just" an autoregressive Transformer, for decoding behavior from neural spiking activity
- We tokenize behavior timeseries by splitting and neural data by patching (a la NDT2/ViT). Thus, the model can ingest most motor brain-computer interface datasets
- NDT3 is "just" an autoregressive Transformer, for decoding behavior from neural spiking activity
- We tokenize behavior timeseries by splitting and neural data by patching (a la NDT2/ViT). Thus, the model can ingest most motor brain-computer interface datasets
Neural Data Transformer 3 is preprinted! We think it can be an off-the-shelf model for all your intracortical motor decoding needs. Decoding gains over your multisession model expected if you have <1.5 hours of data.
February 7, 2025 at 2:21 PM
Neural Data Transformer 3 is preprinted! We think it can be an off-the-shelf model for all your intracortical motor decoding needs. Decoding gains over your multisession model expected if you have <1.5 hours of data.