Skip to content
Sections
>> Trisquel >> Пакети >> etiona >> interpreters >> lua-torch-optim
etiona  ]
[ Източник: lua-torch-optim  ]

Пакет: lua-torch-optim (0~20170208-g656c42a-3)

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
 * CMAES
All 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.

Други пакети, свързани с lua-torch-optim

  • зависимости
  • препоръчани
  • предложени
  • dep: lua-torch-torch7
    Torch Package for Torch Framework
  • dep: lua-torch-xlua
    Lua Extension Package for Torch Framework
  • dep: lua5.1
    Simple, extensible, embeddable programming language
    или luajit
    Just in time compiler for Lua programming language version 5.1

Изтегляне на lua-torch-optim

Изтегляне за всички налични архитектури
Архитектура Големина на пакета Големина след инсталиране Файлове
all 166,5 кБ350 кБ [списък на файловете]