chore: import upstream snapshot with attribution

code/ch13/README.md

@@ -0,0 +1,18 @@
+Sebastian Raschka, 2015
+
+Python Machine Learning - Code Examples
+
+## Chapter 13 - Parallelizing Neural Network Training with Theano
+
+- Building, compiling, and running expressions with Theano
+  - What is Theano?
+  - First steps with Theano
+  - Configuring Theano
+  - Working with array structures
+  - Wrapping things up – a linear regression example
+- Choosing activation functions for feedforward neural networks
+  - Logistic function recap
+  - Estimating probabilities in multi-class classification via the softmax function
+  - Broadening the output spectrum by using a hyperbolic tangent
+- Training neural networks efficiently using Keras
+- Summary

code/ch13/mnist_keras_mlp.py

@@ -0,0 +1,82 @@
+import os
+import struct
+import numpy as np
+import theano
+from keras.utils import np_utils
+from keras.models import Sequential
+from keras.layers.core import Dense
+from keras.optimizers import SGD
+
+
+def load_mnist(path, kind='train'):
+    """Load MNIST data from `path`"""
+    labels_path = os.path.join(path,
+                               '%s-labels-idx1-ubyte'
+                                % kind)
+    images_path = os.path.join(path,
+                               '%s-images-idx3-ubyte'
+                               % kind)
+
+    with open(labels_path, 'rb') as lbpath:
+        magic, n = struct.unpack('>II',
+                                 lbpath.read(8))
+        labels = np.fromfile(lbpath,
+                             dtype=np.uint8)
+
+    with open(images_path, 'rb') as imgpath:
+        magic, num, rows, cols = struct.unpack(">IIII",
+                                               imgpath.read(16))
+        images = np.fromfile(imgpath,
+                             dtype=np.uint8).reshape(len(labels), 784)
+
+    return images, labels
+
+#### Loading the data
+
+X_train, y_train = load_mnist('mnist', kind='train')
+X_test, y_test = load_mnist('mnist', kind='t10k')
+
+#### Preparing the data
+
+X_train = X_train.astype(theano.config.floatX)
+X_test = X_test.astype(theano.config.floatX)
+y_train_ohe = np_utils.to_categorical(y_train)
+
+
+#### Training
+
+np.random.seed(1)
+
+model = Sequential()
+model.add(Dense(input_dim=X_train.shape[1],
+                output_dim=50,
+                init='uniform',
+                activation='tanh'))
+
+model.add(Dense(input_dim=50,
+                output_dim=50,
+                init='uniform',
+                activation='tanh'))
+
+model.add(Dense(input_dim=50,
+                output_dim=y_train_ohe.shape[1],
+                init='uniform',
+                activation='softmax'))
+
+sgd = SGD(lr=0.001, decay=1e-7, momentum=.9)
+model.compile(loss='categorical_crossentropy', optimizer=sgd)
+
+model.fit(X_train, y_train_ohe,
+          nb_epoch=50,
+          batch_size=300,
+          verbose=1,
+          validation_split=0.1,
+          show_accuracy=True)
+
+y_train_pred = model.predict_classes(X_train, verbose=0)
+train_acc = np.sum(y_train == y_train_pred, axis=0) / X_train.shape[0]
+print('Training accuracy: %.2f%%' % (train_acc * 100))
+
+y_test_pred = model.predict_classes(X_test, verbose=0)
+test_acc = np.sum(y_test == y_test_pred, axis=0) / X_test.shape[0]
+print('Test accuracy: %.2f%%' % (test_acc * 100))