Skip to content

Latest commit

 

History

History
57 lines (44 loc) · 2.59 KB

machine_learning.md

File metadata and controls

57 lines (44 loc) · 2.59 KB

How to approach Machine learning

What is Machine learning

Machine learning and data mining

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.

Machine learning tools

tensorflow + keras

Keras is a high-level neural networks API can be used as a simplified interface to tensorflow. Image
Read this article what can we get it from keras w/ tensorflow

install Anaconda3 w/ python 3.6.1.

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

let's run the first neural network tutorial w/ python keras

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)