香港科技大学TensorFlow课件4.pdf

TensorFlow @UST Day 3: RNN Sung Kim <hunkim+tfust@> TensorFlow @UST Day 3: RNN Sung Kim <hunkim+tfust@> Gifts from Google and Line Feedback TensorFlow Mechanics feed data and run graph (operation) sess.run (op, feed_dict={x: x_data}) Build graph using TensorFlow operations update variables in the graph (and return values) Machine Learning Basics •Linear Regression •Logistic Regression (Binary classification) •Softmax Classification •Neural Networks •CNN Linear Regression W = tf.Variable(tf.random_normal([1]), name='weight') b = tf.Variable(tf.random_normal([1]), name='bias') # Our hypothesis XW+b hypothesis = X * W + b # cost/loss function cost = tf.reduce_mean(tf.square(hypothesis - y_train)) GradientDescent # Minimize train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost) Logistic Regression Model? (Hypothesis?) hypothesis = tf.sigmoid(tf.matmul(X, W) + b) Cost? # cost/loss function cost = -tf.reduce_mean(Y * tf.log(hypothesis) + (1 - Y) * tf.log(1 - hypothesis)) GradientDescent =0.01 Softmax Classifier Model? (Hypothesis?) logits = tf.matmul(X,W)+b hypothesis = tf.nn.softmax(logits) Cost? # Cross entropy cost/loss cost = tf.reduce_mean (-tf.reduce_sum(Y * tf.log(hypothesis), axis=1)) GradientDescent train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost) Softmax Classifier Model? (H