Machine learning involves the study of algorithms that can extract information automatically (i.e., without on-line human guidance). Just like data mining, ML (machine learning) is also based on examining large databases in order to generate new information.
In short, machine learning is one step further from data mining; machine learning PREDICTs the next step using the study algorithm.
Here is a long answer for this question.
Keras is a high-level neural networks API can be used as a simplified interface to tensorflow.
Read this article what can we get it from keras w/ tensorflow
Now, We have the official tensorflow installation guide here. but I do not recommend it.
For simplicity, I would recommend to follow this guide below.
Following this guide, you will install Python libraries used for deep learning, specifically: Theano, TensorFlow, and Keras.
here is my configurations;
theano: 0.9.0.dev-c697eeab84e5b8a74908da654b66ec9eca4f1291
tensorflow: 1.2.0
keras: 2.0.5
Once Anaconda + kera is installed, time to run a tutorial.
From this example, we are dealing with indian diabete data. Download it from here (http://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes/pima-indians-diabetes.data)
* For Each Attribute: (all numeric-valued)
1. Number of times pregnant
2. Plasma glucose concentration a 2 hours in an oral glucose tolerance test
3. Diastolic blood pressure (mm Hg)
4. Triceps skin fold thickness (mm)
5. 2-Hour serum insulin (mu U/ml)
6. Body mass index (weight in kg/(height in m)^2)
7. Diabetes pedigree function
8. Age (years)
9. Class variable (0 or 1)