aimacode · norvig · Mar 18, 2017 · Mar 8, 2017 · Mar 18, 2017
diff --git a/learning.py b/learning.py
@@ -434,11 +434,11 @@ def predict(example):


 def NeuralNetLearner(dataset, hidden_layer_sizes=[3],
-                     learning_rate=0.01, epoches=100):
+                     learning_rate=0.01, epochs=100):
    """Layered feed-forward network.
    hidden_layer_sizes: List of number of hidden units per hidden layer
    learning_rate: Learning rate of gradient descent
-    epoches: Number of passes over the dataset
+    epochs: Number of passes over the dataset
    """

    i_units = len(dataset.inputs)
@@ -447,7 +447,7 @@ def NeuralNetLearner(dataset, hidden_layer_sizes=[3],
    # construct a network
    raw_net = network(i_units, hidden_layer_sizes, o_units)
    learned_net = BackPropagationLearner(dataset, raw_net,
-                                         learning_rate, epoches)
+                                         learning_rate, epochs)

    def predict(example):

@@ -510,7 +510,7 @@ def network(input_units, hidden_layer_sizes, output_units):
    return net


-def BackPropagationLearner(dataset, net, learning_rate, epoches):
+def BackPropagationLearner(dataset, net, learning_rate, epochs):
    """[Figure 18.23] The back-propagation algorithm for multilayer network"""
    # Initialise weights
    for layer in net:
@@ -530,7 +530,7 @@ def BackPropagationLearner(dataset, net, learning_rate, epoches):
    o_nodes = net[-1]
    i_nodes = net[0]

-    for epoch in range(epoches):
+    for epoch in range(epochs):
        # Iterate over each example
        for e in examples:
            i_val = [e[i] for i in idx_i]
@@ -583,13 +583,13 @@ def BackPropagationLearner(dataset, net, learning_rate, epoches):
    return net


-def PerceptronLearner(dataset, learning_rate=0.01, epoches=100):
+def PerceptronLearner(dataset, learning_rate=0.01, epochs=100):
    """Logistic Regression, NO hidden layer"""
    i_units = len(dataset.inputs)
    o_units = 1  # As of now, dataset.target gives only one index.
    hidden_layer_sizes = []
    raw_net = network(i_units, hidden_layer_sizes, o_units)
-    learned_net = BackPropagationLearner(dataset, raw_net, learning_rate, epoches)
+    learned_net = BackPropagationLearner(dataset, raw_net, learning_rate, epochs)

    def predict(example):
        # Input nodes