github.com/torch/nn.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2017-07-11	parameters() uses torch.type instead of type	Nicholas Leonard

2016-08-03	memset the result buffers sent into mm (when beta = 0) to zero to fix subtle ↵	Soumith Chintala
	BLAS behavior based bugs
2016-01-13	add locally-connected layers	Kaiyu Yang
	fix a typo problem of returning a number instead of a tensor progressing bias added forward done cannot pass gradient check yet pass all checks add tests in test.lua Update convolution.md add document format the code use floor to compute output width instead of ceil modify checkInput and checkOutput make unfolded_copy and unfolded_acc into separate files add test against nn.SpatialConvolution progressing on SpatialConvolutionLocal.c fix a typo problem of returning a number instead of a tensor progressing bias added forward done cannot pass gradient check yet pass all checks add tests in test.lua Update convolution.md add document format the code use floor to compute output width instead of ceil modify checkInput and checkOutput make unfolded_copy and unfolded_acc into separate files add test against nn.SpatialConvolution fix missing parenthesis add locally-connected layers
2015-07-10	Add unit tests for hessian.lua, fix bugs detected by the tests.	Andrey Golovizin
	* Fix initialization of diagHessianBias for nn.SpatialConvolution. * Fix computing diagHessianBias for nn.SpatialFullConvolution. * Call module:forward() with the proper input before calling accGradParameters(). Without that, accDiagHessianParameters() produces incorrect results for some convolution classes. * Move duplicate code from Module.getParameters() to Module.flatten(), which is now used by both the original Module.getParameters() in Module.lua and the replacement Module.getParameters() in hessian.lua.
2015-05-05	Rename unpack to table.unpack for Lua 5.2	Sam Gross
	Torch7 defines table.unpack to unpack if it is not defined.
2014-11-21	Fix various unused variables in nn	Andrew Tulloch

2013-01-03	New NN classes	koray kavukcuoglu
	extra/nn/L1Cost.lua : L1 penalty extra/nn/SpatialFullConvolution.lua : full convolution extra/nn/SpatialFullConvolutionMap.lua : full convolution with connection table extra/nn/TanhShrink.lua : shrinkage with x-tanh(x) extra/nn/WeightedMSECriterion.lua : mean squared error with weighting mask on the target Add new nn classes that are used commonly for unsupervised training of convolutional auto encoders
2012-11-30	Updated flatten() in hessian.lua to be synchronized the version in ↵	Ivo Danihelka
	Module:getParameters().
2012-09-24	Removed useless print, times 2.	Clement Farabet

2012-09-21	Added an extra corner case to getParameters().	Clement Farabet
	This might finally fix all the possible corners. Fix by Michael Matthieu.
2012-09-14	Fixed flatten function when hessian is activated.	Clement Farabet

2012-07-17	Merge branch 'master' of https://github.com/andresy/torch	Clement Farabet

2012-07-17	Got rid of incorrect hessian implementations.	Clement Farabet

2012-07-13	Fixed outdated call.	Clement Farabet

2012-07-07	Commiting incorrect hessian implementation.	Clement Farabet

2012-07-07	Renaming hessian function	Clement Farabet

2012-07-07	Got rid of some hessian code that didn't belong here.	Clement Farabet

2012-07-06	Oups: missing file.	Clement Farabet