# Overview
-### neuralnetworksanddeeplearning.com integrated scripts for Python 3.4.3 and Theano with CUDA support
+### neuralnetworksanddeeplearning.com integrated scripts for Python 3.5.2 and Theano with CUDA support
-These scrips are updated ones from the **neuralnetworksanddeeplearning.com** gitHub repository in order to fully work with Python 3.4.3.
+These scrips are updated ones from the **neuralnetworksanddeeplearning.com** gitHub repository in order to fully work with latest Pyethon distribution.
-The testing file (**test.py**) contains all three networks (network.py, network2.py, network3.py) and is the starting point to run (i.e. *train and evaluate*) them.
+The testing file (**test.py**) contains all three networks (network.py, network2.py, network3.py) from the book and it is the starting point to run (i.e. *train and evaluate*) them.
# Usage
Just type at shell:
-**python3 test.py**
-
-# Aim
-
-I just want to make other's life easier. Feel free to modify it.
+**python3.5 test.py**
import mnist_loader
training_data, validation_data, test_data = mnist_loader.load_data_wrapper()
+training_data = list(training_data)
# ---------------------
# - network.py example:
-# import network
-# net = network.Network([784, 30, 10])
-# net.SGD(training_data, 30, 10, 3.0, test_data=test_data)
+import network
+net = network.Network([784, 30, 10])
+net.SGD(training_data, 30, 10, 3.0, test_data=test_data)
# ----------------------
# - network2.py example:
-import network2
-net = network2.Network([784, 30, 10], cost=network2.CrossEntropyCost)
-#net.large_weight_initializer()
-net.SGD(training_data, 30, 10, 0.1, lmbda = 5.0,evaluation_data=validation_data, monitor_evaluation_accuracy=True)
+# import network2
+# net = network2.Network([784, 30, 10], cost=network2.CrossEntropyCost)
+# #net.large_weight_initializer()
+# net.SGD(training_data, 30, 10, 0.1, lmbda = 5.0,evaluation_data=validation_data,
+# monitor_evaluation_accuracy=True)
+
+
+# chapter 3 - Overfitting and regularization example
+# import network2
+# net = network2.Network([784, 30, 10], cost=network2.CrossEntropyCost)
+# net.large_weight_initializer()
+# net.SGD(training_data[:1000], 400, 10, 0.5, evaluation_data=test_data,
+# monitor_evaluation_accuracy=True,
+# monitor_training_cost=True)
+
# ----------------------
# - network3.py example: