PulseAugur
EN
LIVE 08:53:59

New MOJO framework boosts neural decoding with self-supervised learning

By PulseAugur Editorial · [2 sources] ·

Researchers have developed MOJO, a novel training framework for spike-tokenizing neural data models. MOJO integrates self-supervised learning via masked autoencoding with supervised learning, enabling the use of unlabeled data. This approach significantly improves decoding performance, especially in low-data scenarios, and generalizes across species and neural modalities like human electrocorticography. AI

IMPACT This research could lead to more flexible and scalable data usage for training neuro-foundation models, improving brain-computer interfaces.

RANK_REASON The cluster contains a research paper detailing a new method for neural data decoding.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New MOJO framework boosts neural decoding with self-supervised learning

COVERAGE [2]

  1. arXiv cs.LG TIER_1 Italiano(IT) · Ximeng Mao, Nanda H. Krishna, Avery Hee-Woon Ryoo, Matthew G. Perich, Guillaume Lajoie ·

    Leveraging unlabelled data for generalizable neural population decoding

    arXiv:2607.14086v1 Announce Type: new Abstract: Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pret…

  2. arXiv cs.LG TIER_1 Italiano(IT) · Guillaume Lajoie ·

    Leveraging unlabelled data for generalizable neural population decoding

    Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding p…

RELATED ENTITIES

RELATED TOPICS