The Computational Graph

1. TF CORE - researchers

2. Library :tf.contrib.learn

3. Computational graph: i.Each node takes zero or more tensors as inputs and produces a tensor as an output. ii.One type of node is a constant, which takes no inputs and it outputs a value it stores internally.   xxxx = tf.constant(initial value, [tf.float32])    [ ] default

4. Session object with method run. xxxx = tf.Session() xxx.run()

5. We can build more complicated computations by combining Tensor nodes with operations. Operations are also nodes.

6. Placeholder can be processed as kind of a "lambda" or a function (parameterized value)  xxxx = tf.placeholder(tf.float32)

    lambda sess.run(a kind of operation, operated feed_dict parameter)  

Especially, operation can act like this: adder_node = a + b            add_and_triple = adder_node * 3

7. Variables allow us to add trainable parameters to a graph.    xxxx = tf.Variable([.3], tf.float32) constructed with a type and initial value. HOWEVER, when you call tf.Variable, variables are not initialized instantly

8. init = tf.global_variables_initializer()

   sess.run(init)

   init is a handle. Until we call sess.run, the variables are uninitialized

9. loss function = cost function

    reduce_sum reduce_xxx is under Reduction in the official document.

    ReductionTensorFlow provides several operations that you can use to perform common math computations that "reduce various dimensions" of a tensor.

10. tf.assign for Variable assignment.