fixed a few more typos

dallascard · dallascard · commit ca7d215c64d6 · 2015-07-12T23:33:17.000-04:00
diff --git a/code/logistic_sgd.py b/code/logistic_sgd.py
@@ -94,11 +94,11 @@ def __init__(self, input, n_in, n_out):
         # symbolic expression for computing the matrix of class-membership
         # probabilities
         # Where:
-        # W is a matrix where column-k represent the separation hyper plain for
+        # W is a matrix where column-k represent the separation hyperplane for
         # class-k
         # x is a matrix where row-j  represents input training sample-j
-        # b is a vector where element-k represent the free parameter of hyper
-        # plain-k
+        # b is a vector where element-k represent the free parameter of
+        # hyperplane-k
         self.p_y_given_x = T.nnet.softmax(T.dot(input, self.W) + self.b)
 
         # symbolic description of how to compute prediction as class whose
diff --git a/code/mlp.py b/code/mlp.py
@@ -296,9 +296,9 @@ def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
     # specify how to update the parameters of the model as a list of
     # (variable, update expression) pairs
 
-    # given two list the zip A = [a1, a2, a3, a4] and B = [b1, b2, b3, b4] of
-    # same length, zip generates a list C of same size, where each element
-    # is a pair formed from the two lists :
+    # given two lists of the same length, A = [a1, a2, a3, a4] and
+    # B = [b1, b2, b3, b4], zip generates a list C of same size, where each
+    # element is a pair formed from the two lists :
     #    C = [(a1, b1), (a2, b2), (a3, b3), (a4, b4)]
     updates = [
         (param, param - learning_rate * gparam)
diff --git a/doc/rnnslu.txt b/doc/rnnslu.txt
@@ -101,7 +101,7 @@ Raw input encoding
 
 A token corresponds to a word. Each token in the ATIS vocabulary is associated to an index. Each sentence is a
 array of indexes (``int32``). Then, each set (train, valid, test) is a list of arrays of indexes. A python
-dictionnary is defined for mapping the space of indexes to the space of words.
+dictionary is defined for mapping the space of indexes to the space of words.
     
     >>> sentence
     array([383, 189,  13, 193, 208, 307, 195, 502, 260, 539,
@@ -224,7 +224,7 @@ The **parameters** of the E-RNN to be learned are:
 * the word embeddings (real-valued matrix) 
 * the initial hidden state (real-value vector)
 * two matrices for the linear projection of the input ``t`` and the previous hidden layer state ``t-1``
-* (optionnal) bias. `Recommendation <http://en.wikipedia.org/wiki/Occam's_razor>`_: don't use it.
+* (optional) bias. `Recommendation <http://en.wikipedia.org/wiki/Occam's_razor>`_: don't use it.
 * softmax classification layer on top
 
 The **hyperparameters** define the whole architecture:
@@ -282,7 +282,7 @@ the true labels and compute some metrics. In this `repo
 <http://www.cnts.ua.ac.be/conll2000/chunking/conlleval.txt>`_ PERL script.
 It's not trivial to compute those metrics due to the `Inside Outside Beginning
 (IOB) <http://en.wikipedia.org/wiki/Inside_Outside_Beginning>`_ representation
-i.e. a prediction is considered correct if the word-beginnin **and** the
+i.e. a prediction is considered correct if the word-beginning **and** the
 word-inside **and** the word-outside predictions are **all** correct.
 Note that the extension is `txt` and you will have to change it to `pl`.
 
