Introduction to machine learning

In this tutorial we will learn about the machine leaning concepts.

Machine learing is the process where we want to teach machine as we do for human beings.

we have to create recommendation engine for a user who watches videoes on youtube on a daily basis, where we have scenario 

.show 10% music related content

.show 20% gaming content

.show 30% eductaion related content

.show 40% other sort of content

so this rule is for everyone , who didn't want education related video. for this , we need machine learing.

Conceept of Learning:

Learning is acquiring new or modifying existing knowledge, behaviours,skills,values and may involve synthesizing different types of informations. It is the improvement of performance with experience overtime.

Learning involves three factors:

1.Changes:

Learning changes the learners. For ML , learning the problem is determining the nature of those changes and how to best represent them.

2.Generalization:

Learning leads to generalization. Performance must improve not only on the same task but  on similar tasks.

3.Improvement:

Learning leads to improvements . ML must address the possibility that changes may degrade performance and find ways to prevent it.

 

Machine Learning:

Machine learning is similar to  data mining. , In both case system search through data to look for patterns. However, instead of extracting data for human comprehension, ML uses ta data to detect patterns and to adjust program actions accordingly.

example: facebook uses the machine learning to personalized each members feed. if a member frequently stops inorder to read or like a particular friend post then newfeed will start to show more of that friend activity in the feed. recommendation syystem is based on machine learning.

Simply, ML is a type of AI that provide computer with the ability to learn without being explicitly programmed.  it focuses on the development of computer programs  that can teach themselves to grow and changes when exposed to new data.

ML is the set of algorithms , which is trained by data and make a model according to the data and finalyy take perform action or prediction based on that data perform specific task.

 

 

Application of ML:

1.Data mining nad knowledge discovery.

2.Speech,video and image recognitation

3.Autonomous vechiles/ robots.

4.Fault detection

5.web mining

6.Market basket analysis

 

Types of Learning:

1.Rote learning

2.Direct Instruction

3.Learning by analogy

4.Inductive Learning

5.Learning by deduction

 

In Machine there are basically three type of learning

1.Supervised learning

2.Unsupervised Learning

3.Reinforcement Learning

 

How Does machine learning works?

ML algo is trained with the training data set to create a model. when a new input data (test data) is introducted to the ML algo, it makes a prediction on the basis of the model. 

The prediction is evaluated for accuracy and if the accuracy is acceptable, The ML algorithm is deployed. if  the accuracy is not acceptable, The ML algo is trained again and again with an augmented training data set.

ML process are similar to Data mining and predicative modeling.

Data mining: Data mining is the process of discovering patterns in large datasets involvibg methods at the intersection of machine learning,statistics and database systems.

predictive modeling: Predictive modeling is the process that uses data mining and probability to forecast outcomes.