The Context-modulated Synaptic-states Recurrent Neural Network (CoSyn-RNN), a new continual-learning model inspired by heterogeneous synaptic states and neuro-modulatory control, is introduced, in which protected synaptic states, sparse allocation, and context-dependent modulation support continual learning.
Yuan Gao, S. Mihalas, Denis Turcu· bioRxiv· 0 citations
This work adopts a biologically plausible saliency-informed dropout technique as an explainable alternative to the unstructured standard random dropout approach and presents empirical results on regimes where such structured dynamic and static sparsities interact optimally to prune a ResNet model on the Imagenette data...
Shira Goldhaber-Gordon, A. Akwaboah, Aaron L. Sampson et al.· International Conference on...· 1 citation
In vivo optical physiology with postmortem electron microscopy is combined to extract neuronal assemblies and shows that these assemblies can serve as functional units of perception and suggest they may be structurally delineated by mutual inhibition.
J. Wagner-Carena, S. Kate, Trevor Riordan et al.· Cell Reports· 0 citations
It is found that basic cell type descriptions often predicted electrical properties better than more complex gene-based methods alone, and when linking data is in the hundreds, simpler representations outperform large general-purpose AI models in isolation, but the two approaches may be complementary rather than compet...
Harshil Sharma, Xiao-Ping Liu, Thomas Chartrand et al.· bioRxiv· 0 citations
A database of spiking activity across the mouse visual system-including the cortex, thalamus, and midbrain-while mice perform an image change detection task is presented, providing a valuable substrate for understanding sensorimotor computations in neural networks.
Corbett Bennett, Samuel D. Gale, Greggory Heller et al.· Cell· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
