Machine Learning with TensorFlow Book: различия между версиями

Материал из Home Wiki
Перейти к навигации Перейти к поиску
 
(не показано 6 промежуточных версий этого же участника)
Строка 22: Строка 22:
Reinforcement learning trains on information gathered by observing how the environment reacts to actions.
Reinforcement learning trains on information gathered by observing how the environment reacts to actions.


= 2 Tensorflow opertators =
= 2. Tensorflow opertators =


tf.constant
tf.constant
Строка 32: Строка 32:
tf.negative
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
== 2.4. Executing operators with sessions ==
<syntaxhighlight>
with tf.Session() as sess:
    result = sess.run(negMatrix)
</syntaxhighlight>
With interactive session remember to close the session to free up resources.
<syntaxhighlight>
sess = tf.InteractiveSession()
...
sess.close()
</syntaxhighlight>
-> 2.4.1


[[Категория:Работа]]
[[Категория:Работа]]

Текущая версия на 20:14, 25 февраля 2018

Категория:Работа

Machine Learning with TensorFlow Book by Nishant Shukla

https://github.com/BinRoot/TensorFlow-Book/

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.

1.4.3 Reinforcement learning

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

2. Tensorflow opertators

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

2.4. Executing operators with sessions

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