Merge pull request #2035 from lamblin/doc_sparse_block_dot

theano/sandbox/cuda/blocksparse.py

@@ -699,6 +699,11 @@ GpuElemwise{mul}(lr, SparseBlockOuterSS) -> SparseBlockOuterSS(..., alpha=lr)
 
 def sparse_block_dot_SS(W, h, inputIdx, b, outputIdx):
     """
+    Compute the dot product (plus bias) of the specified pieces of vectors
+    and matrices.
+
+    Parameters
+    ----------
     var: shape, comment
     W: (iBlocks, oBlocks, iSize, oSize), weight matrix
     h: (batch, iWin, iSize), input from lower layer (sparse)
@@ -706,8 +711,20 @@ def sparse_block_dot_SS(W, h, inputIdx, b, outputIdx):
     b: (oBlocks, oSize), bias vector
     outputIdx: (batch, oWin), indexes of the output blocks
 
-    returns (batch, oBlocks, oSize), dot(W[i, j], h[i]) + b[j]
+    returns (batch, oWin, oSize), dot(W[i, j], h[i]) + b[j]
          but b[j] is only added once
+
+    Notation
+    --------
+    - `batch` is the number of examples in a minibatch (batch size).
+    - `iBlocks` is the total number of blocks in the input (from lower layer).
+    - `iSize` is the size of each of these input blocks.
+    - `iWin` is the number of blocks that will be used as inputs. Which blocks
+      will be used is specified in `inputIdx`.
+    - `oBlocks` is the number or possible output blocks.
+    - `oSize` is the size of each of these output blocks.
+    - `oWin` is the number of output blocks that will actually be computed.
+      Which blocks will be computed is specified in `outputIdx`.
     """
     assert inputIdx.ndim == h.ndim - 1
     assert outputIdx.ndim == inputIdx.ndim