We've created a Tensorflow toolbox for reverse engineering trained RNNs (with @SussilloDavid). You train a network (e.g., "vanilla", LSTM, GRU, custom), then we use TF to do the fixed point optimizations and Jacobian computations. http://joss.theoj.org/papers/10.21105/joss.01003 …
-
-
FixedPointFinder identifies the stable (black) and unstable (red) fixed points, along with linearized dynamics local to each fixed point (red lines are dominant modes). Trajectories of the network state are overlaid in blue.pic.twitter.com/P4vXoqI8Nt
Prikaži ovu nit -
We hope this tool inspires you to unleash modern deep learning approaches toward understanding how networks and brains solve challenging tasks!
Prikaži ovu nit
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.