diff options
author | koray kavukcuoglu <koray@kavukcuoglu.org> | 2012-02-13 09:33:09 +0400 |
---|---|---|
committer | koray kavukcuoglu <koray@kavukcuoglu.org> | 2012-02-13 09:33:09 +0400 |
commit | 7bb7d7d2bbc2ec7499bc77a2334fbcb35e045958 (patch) | |
tree | 3850d20c703b851563ca817c87eea1903c33ed58 | |
parent | e39ed8bc955c112029789e93e208f813eeaa20e5 (diff) |
big pass over documentation to make titles consistent across all packages..
-rw-r--r-- | doklua/index.dok | 14 | ||||
-rw-r--r-- | doktutorial/index.dok | 26 |
2 files changed, 20 insertions, 20 deletions
diff --git a/doklua/index.dok b/doklua/index.dok index 6baad95..8728c6b 100644 --- a/doklua/index.dok +++ b/doklua/index.dok @@ -13,7 +13,7 @@ information, or have a look on the [[LuaManual|Lua Reference Manual]]. ===== Why choose Lua? ===== -=== Lua is a proven and robust language === +==== Lua is a proven and robust language ==== Lua has been used in [[http://www.lua.org/uses.html|many industrial applications]] (e.g., @@ -25,7 +25,7 @@ is currently the leading scripting language in games. Lua has a solid [[http://www.lua.org/versions.html|versions]] of Lua have been released and used in real applications since its creation in 1993. -=== Lua is fast === +==== Lua is fast ==== Lua has a deserved reputation for performance. To claim to be "as fast as Lua" is an aspiration of other scripting @@ -34,7 +34,7 @@ of interpreted scripting languages. Lua is fast not only in fine-tuned benchmark programs, but in real life too. A substantial fraction of large applications have been written in Lua. -=== Lua is portable === +==== Lua is portable ==== Lua is [[http://www.lua.org/download.html|distributed]] in a small package that builds out-of-the-box in all platforms that have an ''ANSI/ISO C'' @@ -43,7 +43,7 @@ devices (such as handheld computers and cell phones that use ''BREW'', ''Symbian ''Pocket PC'', etc.) and embedded microprocessors (such as ''ARM'' and ''Rabbit'') for applications like ''Lego MindStorms''. -=== Lua is embeddable === +==== Lua is embeddable ==== Lua is a fast language engine with small footprint that you can embed into your application. Lua has a simple and well documented ''API'' that allows @@ -55,7 +55,7 @@ extend programs written not only in ''C'' and ''C++'', but also in ''Java'', ''C such as ''Perl'' and ''Ruby''. -=== Lua is simple and powerful === +==== Lua is simple and powerful ==== A fundamental concept in the design of Lua is to provide //meta-mechanisms// for implementing features, instead of providing a host of features directly @@ -65,14 +65,14 @@ inheritance. Lua's meta-mechanisms bring an economy of concepts and keep the language small, while allowing the semantics to be extended in unconventional ways. -=== Lua is free === +==== Lua is free ==== Lua is free software, distributed under a [[http://www.lua.org/license.html|liberal license]] (the well-known ''MIT'' license). It can be used for both academic and commercial purposes at absolutely no cost. Just [[http://www.lua.org/download.html|download]] it and use it. -===== Where does Lua come from? ===== +==== Where does Lua come from? ==== Lua is designed and implemented by a team at [[http://www.puc-rio.br/|PUC-Rio]], the Pontifical Catholic University of diff --git a/doktutorial/index.dok b/doktutorial/index.dok index a11a95e..b424a14 100644 --- a/doktutorial/index.dok +++ b/doktutorial/index.dok @@ -10,7 +10,7 @@ vectors, matrices and tensors and how to build and train a basic neural network. For anything else, you should know how to access the html help and read about how to do it. -====== What is Torch? ====== +===== What is Torch? ===== Torch7 provides a Matlab-like environment for state-of-the-art machine learning algorithms. It is easy to use and provides a very efficient @@ -18,14 +18,14 @@ implementation, thanks to a easy and fast scripting language (Lua) and an underlying C/C++ implementation. You can read more about Lua [[http://www.lua.org|here]]. -====== Installation ====== +===== Installation ===== First before you can do anything, you need to install Torch7 on your machine. That is not described in detail here, but is instead described in the [[..:install:index|installation help]]. -====== Checking your installation works and requiring packages ====== +===== Checking your installation works and requiring packages ===== If you have got this far, hopefully your Torch installation works. A simple way to make sure it does is to start Lua from the shell command line, @@ -55,7 +55,7 @@ or higher-dimensional objects (tensors). Tensors). To see the list of all packages distributed with Torch7, click [[..:index|here]]. -====== Getting Help ====== +===== Getting Help ===== There are two main ways of getting help in Torch7. One way is ofcourse the html formatted help. However, another and easier method is to use @@ -100,7 +100,7 @@ t7> torch.randn( </file> -====== Torch Basics: Playing with Tensors ====== +===== Torch Basics: Playing with Tensors ===== Ok, now we are ready to actually do something in Torch. Lets start by constructing a vector, say a vector with 5 elements, and filling the @@ -229,7 +229,7 @@ t7> =torch.mm(a,b) </file> -====== Types in Torch7 ====== +===== Types in Torch7 ===== In Torch7, different types of tensors can be used. By default, all tensors are created using ''double'' type. ''torch.Tensor'' is a @@ -244,12 +244,12 @@ t7> =torch.Tensor() [torch.FloatTensor with no dimension] </file> -====== Example: training a neural network ====== +===== Example: training a neural network ===== We will show now how to train a neural network using the [[..:nn:index|nn]] package available in Torch. -===== Torch basics: building a dataset using Lua tables ===== +==== Torch basics: building a dataset using Lua tables ==== In general the user has the freedom to create any kind of structure he wants for dealing with data. @@ -302,7 +302,7 @@ for i=1,dataset:size() do end </file> -===== Torch basics: building a neural network ===== +==== Torch basics: building a neural network ==== To train a neural network we first need some data. We can use the XOR data we just generated in the section before. Now all that remains is to define @@ -336,7 +336,7 @@ mlp:add(nn.Linear(HUs,outputs)) </file> -===== Torch basics: training a neural network ===== +==== Torch basics: training a neural network ==== Now we're ready to train. This is done with the following code: @@ -373,7 +373,7 @@ See the nn package description of the for more details. -===== Torch basics: testing your neural network ===== +==== Torch basics: testing your neural network ==== To test your network on a single example you can do this: <file lua> @@ -402,7 +402,7 @@ t7> x=torch.Tensor(2); x[1]=-0.5; x[2]=-0.5; print(mlp:forward(x)) [torch.DoubleTensor of dimension 1] </file> -===== Manual Training of a Neural Network ===== +==== Manual Training of a Neural Network ==== Instead of using the [[..:nn:index#nn.StochasticGradient|StochasticGradient]] class you can directly make the forward and backward calls on the network yourself. @@ -448,7 +448,7 @@ end Super! -====== Concluding remarks ====== +===== Concluding remarks ===== That's the end of this tutorial, but not the end of what you have left to discover of Torch! To explore more of Torch, you should take a look |