Gabriel Mahuas

CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding

A novel contrastive-pretrained EEG model with multiscale temporal convolution input layers and Transformer encoder blocks (CoCoT), demonstrating the viability of contrastive learning for building EEG FMs while suggesting key architectural design considerations, prompting further investigations in alternative large-scal...