What is Machine Learning ?
Prakash Software Pvt. Ltd.
What is Machine Learning ?

Machine learning (ML) is a category of algorithm that allows software applications to become more accurate in predicting outcomes without being explicitly programmed.

What machine learning does :

  • Find patterns in data which we have provided and uses those patterns to predict the future.
  • You do have enough data that people just get can find pattern on those data.

Why to learn ml ?

  • You need to know at least basics of this technology because ML is so important it becomes bigger and bigger part of our life day by day.
  • Application in machine learning

ML cycle

  • Ask a right question
  • Choose right data
  • Get that data in to good shape
  • Iterate until you have a model that makes a good predictions.
  • Rebuild that model periodically
  • Deploy that model

How to choose right data

  • Truth is that, you waste most of time to getting clean n prepare data. And that’s quite logical.
  • Choose data which are more predictive.
  • There could be duplicate and missing data, data has extra stuffs.

So need to apply pre-processing to make data more accurate.

Machine learning in Nutshell

  • Choose data which are more predictive.
  • pre-processing on that data : Data has duplicate and missing data also has extra stuffs in to that.
  • Truth is that you waste most of time to getting clean n prepare data.
  • Learning and choosing algorithm on to that data.
  • 1st model is candidate model.
  • Deploy chosen model and give it to application.

Terminology

picture1

What machine learning does

  • Identify patterns
  • Recognize that patterns when you see it again

Algorithms

Choose right algorithm

  • Any Classification Algorithm
  • Any Clustering Algorithm
  • Any Regression Algorithm
  • Any Recommendation Algorithm

Classification Algorithm

your problem statement is a question to classify something(i.e. Is this good or bad?) or when your goal is to predict discrete values, e.g. {1,0}, {True, False}, {Spam, No Spam}.

Classification is a Supervised Learning. 

Example of Classification Algorithm:

  • K – Nearest neighbor
  • Decision Trees
  • Bayesian Classifier

Clustering Algorithm

  • When you have large social network site and you want to divide the users on basis of the Likes they made on the post or on basis of Demographics, so it helps to identify the meaningful groups.
  • Clustering is an Unsupervised Learning.

Regression Algorithm

  • Whenever you are told to predict some future value of a process which is currently  running, you can go with Regression Algorithm.
  • Regression is a Supervised Learning.
  • Scenario : How long it would take me to go Home from my office ?
  • Example of Regression Algorithm:
  • Linear Regression Algorithm
  • Logistic Regression Algorithm
  • Polynomial Regression Algorithm etc
  • Recommendation Algorithm
  • when you want to determine what kind of theme a user would like in future based on the user’s past behavior.

E.g., If a user buys the Washing Machine, what else he would buy in future

Top 8 Programming Languages For Machine Learning & Data Science:

  • Python.
  • Java.
  • R.
  • C++
  • C.
  • JavaScript.
  • Scala.
  • Julia.

Azure machine learning studio

picture11

ML.NET

  • ML.Net is a free, cross-platform, open source machine learning framework made specifically for .NET developers.
  • Create sample in .Net
  • ML.Net : currently in preview