Small doc typo fixes

doc/library/tensor/nnet/conv.txt

@@ -29,17 +29,17 @@ TODO: Give examples for how to use these things! They are pretty complicated.
     - :func:`nnet.conv2d <theano.tensor.nnet.conv.conv2d>`.
     - :func:`conv3D <theano.tensor.nnet.Conv3D.conv3D>`.
     - :func:`conv3d2d <theano.tensor.nnet.conv3d2d.conv3d>`
-      Another conv3d implementation that use the conv2d with data reshaping.
-      It is faster in some case then conv3d, specificaly on the GPU.
+      Another conv3d implementation that uses the conv2d with data reshaping.
+      It is faster in some cases than conv3d, specifically on the GPU.
     - `Faster conv2d <http://deeplearning.net/software/pylearn2/library/alex.html>`_
 
-      This is in Pylearn2, not very documented and use a different
-      memory layout for the input.  It is important to have the input
+      This is in Pylearn2, not very documented and uses a different
+      memory layout for the input. It is important to have the input
       in the native memory layout, and not use dimshuffle on the
-      inputs, otherwise you loose much of the speed up. So this is not
+      inputs, otherwise you lose most of the speed up. So this is not
       a drop in replacement of conv2d.
 
-      Normally those are called from the `linear transfrom
+      Normally those are called from the `linear transform
       <http://deeplearning.net/software/pylearn2/library/linear.html>`_
       implementation.