Pakket: lua-torch-optim (0~20170208-g656c42a-3)
Verwijzigingen voor lua-torch-optim
Trisquel bronnen:
Het bronpakket lua-torch-optim downloaden:
- [lua-torch-optim_0~20170208-g656c42a-3.dsc]
- [lua-torch-optim_0~20170208-g656c42a.orig.tar.gz]
- [lua-torch-optim_0~20170208-g656c42a-3.debian.tar.xz]
Beheerder:
Original Maintainers:
- Debian Science Maintainers (Mailarchief)
- Mo Zhou
Externe bronnen:
- Homepage [github.com]
Vergelijkbare pakketten:
Numeric Optimization Package for Torch Framework
This package contains several optimization routines and a logger for Torch.
The following algorithms are provided:
* Stochastic Gradient Descent * Averaged Stochastic Gradient Descent * L-BFGS * Congugate Gradients * AdaDelta * AdaGrad * Adam * AdaMax * FISTA with backtracking line search * Nesterov's Accelerated Gradient method * RMSprop * Rprop * CMAESAll these algorithms are designed to support batch optimization as well as stochastic optimization. It's up to the user to construct an objective function that represents the batch, mini-batch, or single sample on which to evaluate the objective.
This package provides also logging and live plotting capabilities via the `optim.Logger()` function. Live logging is essential to monitor the network accuracy and cost function during training and testing, for spotting under- and over-fitting, for early stopping or just for monitoring the health of the current optimisation task.
Andere aan lua-torch-optim gerelateerde pakketten
|
|
|
-
- dep: lua-torch-torch7
- Torch Package for Torch Framework
-
- dep: lua-torch-xlua
- Lua Extension Package for Torch Framework