Why should you learn Machine Learning?

How to solve real world problems?

It is hard to write programs that solves problems, like recognising a three dimensional object, translate one language to another or understand the sentiments of a person .

We don’t know what program to write because we don’t know how it is done in our brain

Even if we had a good idea about writing a program it will be very complicated

It is hard to write a program to detect a fraudulent transaction. There may not be any simple and reliable rules. We need to add some large number of not very reliable rules.

These rules may change every time. Program needs to keep changing.

The Machine Learning Approach 

Instead of writing program by hand for each specific task, we collect lot of examples that specify the correct output for a given input.

A machine learning algorithm then takes these examples and produces a program that does the job

The program produced by the machine learning algorithm may look different from a handwritten program

If we do it right the program created works for new cases as well as what  it was trained on

If the data changes, the program then changes to train on new data

Some tasks best solved by Machine Learning

Recognising patterns

Real Life objects

Facial Expressions

Recognising anomalies

Unusual sequence of credit card transaction

Prediction

Future stock prices

House prices

Which movie person may like

How do I start with Machine Learning?

A predictive modeling machine learning project can be broken down into 6 top-level tasks:

1. Define Problem: Investigate and characterise the problem in order to better understand
the goals of the project.

2. Analyse Data: Use descriptive statistics and visualisation to better understand the data
you have available.

3. Prepare Data: Use data transforms in order to better expose the structure of the
prediction problem to modeling algorithms.

4. Evaluate Algorithms: Design a test harness to evaluate a number of standard algorithms
on the data and select the top few to investigate further.

5. Improve Results: Use algorithm tuning and ensemble methods to get the most out of
well-performing algorithms on your data.

6. Present Results: Finalize the model, make predictions and present results.

 

Read also: Docker Container for New Data Scientists

Tagged with:

Manish Prasad

An experienced data scientists with huge passion for working on new challenges.

To give you the best possible experience, this site uses cookies. Continuing to use jamieai.com means you agree on our use of cookies.
Accept