module = SplitTable(dimension)

Creates a module that takes a Tensor as input and outputs several tables, splitting the Tensor along dimension dimension.

Example 1: 

require "lab"
mlp=nn.SplitTable(2)
x=lab.randn(4,3)
pred=mlp:forward(x)
for i,k in pairs(pred) do print(i,k); end
gives the output: 
1
 1.3885
 1.3295
 0.4281
-1.0171
[torch.Tensor of dimension 4]

2
-1.1565
-0.8556
-1.0717
-0.8316
[torch.Tensor of dimension 4]

3
-1.3678
-0.1709
-0.0191
-2.5871
[torch.Tensor of dimension 4]

Example 2: 

require "lab"
mlp=nn.SplitTable(1)
pred=mlp:forward(lab.randn(10,3))
for i,k in pairs(pred) do print(i,k); end
gives the output: 
1
 1.6114
 0.9038
 0.8419
[torch.Tensor of dimension 3]

2
 2.4742
 0.2208
 1.6043
[torch.Tensor of dimension 3]

3
 1.3415
 0.2984
 0.2260
[torch.Tensor of dimension 3]

4
 2.0889
 1.2309
 0.0983
[torch.Tensor of dimension 3]

A more complicated example: 

require "lab"

mlp=nn.Sequential();       --Create a network that takes a Tensor as input
mlp:add(nn.SplitTable(2))
 c=nn.ParallelTable()      --The two Tensors go through two different Linear
 c:add(nn.Linear(10,3))	   --Layers in Parallel
 c:add(nn.Linear(10,7))
mlp:add(c)                 --Outputing a table with 2 elements
 p=nn.ParallelTable()      --These tables go through two more linear layers
 p:add(nn.Linear(3,2))	   -- separately.
 p:add(nn.Linear(7,1)) 
mlp:add(p) 
mlp:add(nn.JoinTable(1))   --Finally, the tables are joined together and output. 

pred=mlp:forward(lab.randn(10,2))
print(pred)

for i=1,100 do             -- A few steps of training such a network.. 
 x=lab.ones(10,2);
 y=torch.Tensor(3); y:copy(x:select(2,1,1):narrow(1,1,3))
 pred=mlp:forward(x)

 criterion= nn.MSECriterion()
 local err=criterion:forward(pred,y)
 local gradCriterion = criterion:backward(pred,y);
 mlp:zeroGradParameters();
 mlp:backward(x, gradCriterion); 
 mlp:updateParameters(0.05);

 print(err)
end