Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Representations (SRs), which model the expected discounted distribution of future states rather than the immediate next state. We transfer this frame...
This Perspective argues that AI-mediated BCIs should be evaluated not only by decoding accuracy and task performance, but also by how AI assistance is deployed: when systems act autonomously, seek confirmation, preserve user effort or return control to the user.
Deriving open-vocabulary mutual information (OVMI), an information-theoretic quantity that measures the information conveyed by a decoder relative to a reference distribution over the words a user may wish to communicate, provides the speech BCI community with a principled way to compare heterogeneous systems, improve...
D. Jayalath, Benjamin Ballyk, Oiwi Parker Jones· 3 citations
A decorrelated, clinician-aligned symptom signal readable directly from internal activations is revealed, offering a mechanistic foundation for interpretable depression-assessment tools.
Fang-Ying Zhu, Ajay K. Subramanian, A. Constant et al.· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
Evidence for reliable cross-subject five-vowel decoding is limited within this dataset and protocol, and the benchmark provides a reproducible chain from source rows to retained epochs, predictions, participant-level metrics, multiplicity-adjusted inference, and bounded diagnostic analyses.
Xiao-Yan Li, Ze-Yan Tao· Journal of Neural Engineerin...· 0 citations
Whether passively-collected keystroke timing dissociates a variability-based pre-error monitoring signal from a speed-based post-error recovery signal from a speed-based post-error recovery signal is tested.
It is shown that an explicit information bottleneck forcing a recurrent neural network to learn a low-dimensional representation is necessary for rotational and out-of-distribution generalisation in a time-series prediction task, and the ability of neural networks to learn compact, distributed and emergent representati...
Hardik Rajpal, Dan Goodman· arXiv.org· 0 citations
It is argued that RCBM provides a promising framework for understanding the nature of cognition, and that it can be used to develop more sophisticated models of cognition in the future.
Teun van Gils, R. Sommers, M. Ostarek et al.· 0 citations
A novel system of ``perforated''backpropagation empowering the artificial neurons of deep neural networks to achieve better performance coding for the same features they coded for in the original architecture is explored.
This work introduces a signed multilayer community detection framework that incorporates both correlated and anti-correlated brain activity to identify subject-specific community structures across tasks and sessions and offers a promising foundation for precision neuroimaging and personalized neuroscience applications.
It is demonstrated that deep latent representations extract clinically relevant signatures from noisy signals, enabling precise, rapid, and data-efficient diagnosis.
PH-attention is introduced, a Pearce--Hall-inspired rule with an explicit feature-indexed associability state that yields cue-dependent learning rates and is absent from the token-computed gates the authors compare, and predicts a dissociation that survives training on generic in-context association.
Mu Qiao· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
