Question

Load MNIST data set. Use data transformations a classification algorithm(s) of your choice to achieve greater than 95% accuracy in cross-validation (cv = 3). There are many ways to achieve, so there are many correct answers. Use only algorithms that we studied(SGD is preferred).KNN is forbidden! Hint: Data is big, look for more efficient algorithms. Start with simple models, make it complex if needed. On you computer the code should run less than 30 minutes. I have a fast computer, it should run less 30 minutes on my as well.

given code：

from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')
X = mnist.data
y = mnist.target

Answer 1

 training_images = training_images / 255.0 test_images = test_images / 255.0 model = tf.keras.models.Sequential([tf.keras.layers.Flatten(), tf.keras.layers.Dense(128, activation=tf.nn.relu), tf.keras.layers.Dense(10, activation=tf.nn.softmax)]) model.compile(optimizer = tf.train.AdamOptimizer(), loss = 'sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(training_images, training_labels, epochs=10) model.evaluate(test_images, test_labels) #we can achieve accuracy upto 90 % by this deep learning algoritham #further we can apply convolution to extract features and apply the algoritham def create_model(): model = tf.keras.models.Sequential() model.add(tf.keras.layers.BatchNormalization(input_shape=x_train.shape[1:])) model.add(tf.keras.layers.Conv2D(64, (5, 5), padding='same', activation='elu')) model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2), strides=(2,2))) model.add(tf.keras.layers.Dropout(0.25)) model.add(tf.keras.layers.BatchNormalization(input_shape=x_train.shape[1:])) model.add(tf.keras.layers.Conv2D(128, (5, 5), padding='same', activation='elu')) model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2))) model.add(tf.keras.layers.Dropout(0.25)) model.add(tf.keras.layers.BatchNormalization(input_shape=x_train.shape[1:])) model.add(tf.keras.layers.Conv2D(256, (5, 5), padding='same', activation='elu')) model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2), strides=(2,2))) model.add(tf.keras.layers.Dropout(0.25)) model.add(tf.keras.layers.Flatten()) model.add(tf.keras.layers.Dense(256)) model.add(tf.keras.layers.Activation('elu')) model.add(tf.keras.layers.Dropout(0.5)) model.add(tf.keras.layers.Dense(10)) model.add(tf.keras.layers.Activation('softmax')) return model