ConcatTable is a container module that applies each member module to the same input Tensor.

Example: 

mlp= nn.ConcatTable()
mlp:add(nn.Linear(5,2))
mlp:add(nn.Linear(5,3))

require "lab"
pred=mlp:forward(lab.randn(5));
for i,k in pairs(pred) do print(i,k); end
which gives the output: 
1
-0.4073
 0.0110
[torch.Tensor of dimension 2]

2
 0.0027
-0.0598
-0.1189
[torch.Tensor of dimension 3]