Machine Learning
By Sumit Kumar Pandey
Introduction
What is Machine Learning?
Using data to answer questions.
According to Wikipedia, “Machine learning is a field of artificial
intelligence that uses statistical techniques to give computer
systems the ability to "learn" (e.g., progressively improve
performance on a specific task) from data, without being
explicitly programmed.”
Computer
Data
Program
Output
ComputerData
Output
Program
Other programming vs Machine learning
Traditional programming
Machine learning
Applications of ML
Examples of ML
Types of Machine Learning
Supervised Learning
• Supervised learning is the machine learning task of
learning a function that maps an input to an
output based on example input-output pairs
Let’s look a bit into Supervised ML
Explanation of previous slide :
• We train the baby for these two example(training set) and explain
the labels that red colour spherical item is apple and yellow colour
cylindrical item is banana and for the third example red colour
cylindrical item we ask for what it is .
• From the previous experience that cylindrical item is banana baby
decide that it may be banana.
Unsupervised Learning
• Unsupervised learning is a branch of machine learning
that learns from test data that has not been labeled,
classified or categorized. Instead of responding to
feedback, unsupervised learning identifies commonalities
in the data and reacts based on the presence or absence
of such commonalities in each new piece of data.
Let’s look deeper into Unsupervised ML
Explanation of previous slide:
• In this we show the image of dogs and cats to baby but in that
there is no labels like red or spherical etc. just like in supervised
learning. So baby did not decide but it can analyze that 1,3,5 are
similar things and 2,4 are similar things and according to that baby
separated the similar items .
• The separation of the similar items is know as clustering . This is
mostly use in unsupervised learning.
Languages Used in Machine Learning
Scope of Machine Learning
Biggest Confusion: AI vs ML vs Deep Learning
Don’t use Machine learning if.....
Not enough data
Not quality labelled data
Don’t use for network traffic analysis
Not enough domain expertise to engineer features
Thank You
Sumit Kumar Pandey
B.Tech., CSE, 3rd Year
Gurukula kangri university

Machine learning

  • 1.
  • 2.
    Introduction What is MachineLearning? Using data to answer questions. According to Wikipedia, “Machine learning is a field of artificial intelligence that uses statistical techniques to give computer systems the ability to "learn" (e.g., progressively improve performance on a specific task) from data, without being explicitly programmed.”
  • 3.
    Computer Data Program Output ComputerData Output Program Other programming vsMachine learning Traditional programming Machine learning
  • 4.
  • 5.
  • 6.
  • 7.
    Supervised Learning • Supervisedlearning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs
  • 8.
    Let’s look abit into Supervised ML
  • 9.
    Explanation of previousslide : • We train the baby for these two example(training set) and explain the labels that red colour spherical item is apple and yellow colour cylindrical item is banana and for the third example red colour cylindrical item we ask for what it is . • From the previous experience that cylindrical item is banana baby decide that it may be banana.
  • 10.
    Unsupervised Learning • Unsupervisedlearning is a branch of machine learning that learns from test data that has not been labeled, classified or categorized. Instead of responding to feedback, unsupervised learning identifies commonalities in the data and reacts based on the presence or absence of such commonalities in each new piece of data.
  • 11.
    Let’s look deeperinto Unsupervised ML
  • 12.
    Explanation of previousslide: • In this we show the image of dogs and cats to baby but in that there is no labels like red or spherical etc. just like in supervised learning. So baby did not decide but it can analyze that 1,3,5 are similar things and 2,4 are similar things and according to that baby separated the similar items . • The separation of the similar items is know as clustering . This is mostly use in unsupervised learning.
  • 13.
    Languages Used inMachine Learning
  • 14.
  • 15.
    Biggest Confusion: AIvs ML vs Deep Learning
  • 16.
    Don’t use Machinelearning if..... Not enough data Not quality labelled data Don’t use for network traffic analysis Not enough domain expertise to engineer features
  • 17.
    Thank You Sumit KumarPandey B.Tech., CSE, 3rd Year Gurukula kangri university