FORCE training with slow learning rates leads to strongly correlated and swapable decoders across spiking LIF and LIF-matched rate networks.

A–C Networks of 2000 neurons were trained on different supervisors over a grid of points in the (Q,G) parameter space for both spiking LIF and LIF-matched rate networks. The learning rates used were: , , and for the pitchfork, Ode to...

Celý popis

Uloženo v:

Podrobná bibliografie
Hlavní autor:	Thomas Robert Newton (21756023) (author)
Další autoři:	Wilten Nicola (4951927) (author)
Vydáno:	2025
Témata:	Cell Biology Neuroscience Science Policy Biological Sciences not elsewhere classified supervised learning tasks slower learning rates slow learning rates longer fully interchangeable fast learning rates force hyperparameters identical force effectively act trial firing rate spiking network could matched instantaneous rate applied force training fire spiking networks spiking networks approximate force trained spiking decoding solutions learned rate network matched rate force training spiking networks rate networks training networks weights trained spiking neurons weight solutions weight matrices vice versa successful convergence selectively stabilizing results indicate principal components pass filter neural bases little effect leaky integrate inherent spike increasing instability findings suggest analytic derivation
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

FORCE training with slow learning rates leads to strongly correlated and swapable decoders across spiking LIF and LIF-matched rate networks.

Podobné jednotky