Chapter 1 1.4.1 Supervised learning

Descrete with few values - Classifier

Many values and the values have natural order - Regressor

1.4.2. Unsupervised learning

Clustering is the process of splitting the data into individual buckets of similar items.

Dimensionality reduction is about manipulating the data to view it under a much simpler perspective.

Reinforcement learning trains on information gathered by observing how the environment reacts to actions.

tf.constant

tf.zeros

tf.ones

tf.negative

tf.add(x, y)—Adds two tensors of the same type, x + y

tf.subtract(x, y)—Subtracts tensors of the same type, x – y

tf.multiply(x, y)—Multiplies two tensors element-wise

tf.pow(x, y)—Takes the element-wise x to the power of y

tf.exp(x)—Equivalent to pow(e, x), where e is Euler’s number (2.718 ...)

tf.sqrt(x)—Equivalent to pow(x, 0.5)

tf.div(x, y)—Takes the element-wise division of x and y

tf.truediv(x, y)—Same as tf.div, except casts the arguments as a float

tf.floordiv(x, y)—Same as truediv, except rounds down the final answer into an integer

tf.mod(x, y)—Takes the element-wise remainder from division

with tf.Session() as sess:
    result = sess.run(negMatrix)

With interactive session remember to close the session to free up resources.

sess = tf.InteractiveSession()
...
sess.close()

-> 2.4.1