Skip to main content

How Machine Learning (ML) Work

How Machine Learning (ML) Work

In this post, We will learn how machine learning work.

What is machine learning (ML) ?

Machine learning is a study of model that compute use to progressively improve their performance on a specific task.

What is Machine learning models ?

Machine learning model contains a set of instruction or mathematical formula or in simple word it contain a piece of code in which we provide some data as input and model return some output. We learn more about model and how use a machine leaning model latter.

How Machine Learning (ML) Work  ?

This part we will understand with an example. Suppose want to have a simple application which will take a picture and banana or apple and application will tell us either it is banana or apple or picture is neither banana nor apple.
To solve this problem first we provide a set of banana picture to our model and we will tell our model that this is a banana picture similarly we will provide a set of apple picture to our model and we will tell our model that this is apple picture. 
From these picture our mode our model will extract some properties of banana and apple like
Banana
  • Shape is cylindrical 
  • Colour is yellow
Apple
  • Shape is spherical
  • Colour is red  
Above two properties are only for understanding this example but in real there would be more properties. So now our model know how a banana and an apple look like. So now if we provide another picture to our model it will calculate the properties of this newly image and match its properties with already calculated properties and if matching is more close to banana means our new image is banana and if matching is more close to apple means our new image is apple.

Training and Testing of Machine Model

In training we teach our model how to behave, like in above example we train our model by providing initial set image to model and its name (Banana or Apple). In testing we provide input and our model predict out put, like after training our model had properties of banana and apple so in testing we provide another image as input to model and this time we do not provide information to model that image is of banana or apple instead our model calculate properties and predict output.

Please write comments if you find anything incorrect, or you want to share more information about the topic discussed above.

    

Comments

  1. Thanks for your nice post, Machine LearningMachine Learning is steadily moving away from abstractions and engaging more in business problem solving with support from AI and Deep Learning. With Big Data making its way back to mainstream business activities,For more informations visit Pridesys IT Ltd

    ReplyDelete

Post a Comment

Popular posts from this blog

SSC Practice Problem Solution

SSC Practice Problem Solution In this post, we will discuss solution of  SSC Practice Problem . Question 1  The efficiency of (A + B) = 100/24 = (25/6)% The efficiency of (A + B + C) = 100/8 = (25/2)% The efficiency of C = 25/2 – 25/6 = (50/6)% Hence, C can alone finish this job in = 100/(50/6) = 12 days Answer: 12 days option (1) Question 2  Original price = Rs. 6000; Price after discount = 6000 – 1200 = Rs. 4800; Price after raising service contract = 4800 + 480 = Rs. 5280 Answer: Rs. 5280 option (2) Question 3  Suppose the received money by A, B, and C is respectively 5x, 6x, and 9x. 5x = 450; => x = 90; Hence, the total money = 20x = 20*90 = Rs. 1800; Answer: Rs. 1800 option (2) Question 4 Suppose the Cost price of the bag= Rs. x; Hence, x + 0.15x = 230; => x = Rs. 200; Selling price after selling on 20% = 200 + 20% of 200 = Rs. 240 Answer: Rs. 240 option (3) Question 5  The required percentage ...

Average

Average In this post, We will learn about average.  Average of any collection of data is the sum of data divide by number of data. Average = (Sum of observations /  Number of observations) Please write comments if you find anything incorrect, or you want to share more information about the topic discussed above.  problems The arithmetic mean of x, y and z is 80, and that of x, y, z, u and v is 75, where u=(x+y)/2 and v=(y+z)/2. If x ≥ z, then the minimum possible value of x is (CAT 2018) As specified in the question mean of x and y and z is 80 x+y+z=3*80 mean of x, y, z,u,v is 75 x+y+z+u+v=75*5 2u=x+y 2v=y+z x+y+z+((x+y+y+z)/2)=75*5 y+3(x+y+z)=75*10 y=750-720 y=30 since x+y+z=240 y=30 so x+z=210 since x>=z so minimum value of x=210/2 = 105 Problem2: In first 5 inings sehwag has scored at average of 40. In sixth ining He had scored 52 what is His average after 6th ining. one simple approach is getting total score divided by no of inin...

Complex Number

Complex Number While solving the equation of the form  a x 2 + b x + c = 0 , the roots of the equations can take three forms which are as follows: Two Distinct Real Roots Similar Root No Real roots (Complex Roots) The introduction of complex numbers in the 16th century made it possible to solve the equation  x 2 + 1 = 0 . The roots of the equation are of the form  x = ± − 1 ‾ ‾ ‾ √  and no real roots exist. Thus, with the introduction of complex numbers, we have Imaginary roots. We denote  − 1 ‾ ‾ ‾ √  with the symbol i, where i denotes Iota (Imaginary number). An equation of the form z= a+ib, where a and b are real numbers, is defined to be a complex number. The real part is denoted by Re z = a and the imaginary part is denoted by Im z = b. Algebraic Operation on Complex numbers: Addition of two complex numbers Subtraction of two complex number Multiplication of two complex number Division of two complex number Power of Iota (i) ...

Logarithm

Logarithm When a x   = N , then we say that x = logarithm of N to the base a and write it as x = log a N . In simple words, it represents the power to which a number must be raised. Let me expand on that by giving a simpler example. If we are asked, what would be the result if ‘a’ is multiplied with itself ‘b’ times; then your answer would be x = a*a*a*…. b (times). This can also be written as a^b. This is also known as ‘a raised to the power of b’ If we are asked, which number multiplied with itself ‘b’ times, will result in a; then you are asked for the value of x such that x*x*x*… b(times) = a => x^b = a => x = a^(1/b) This is also known as ‘bth root of a’ If swe are asked, how many times should you multiply ‘a’ with itself to get ‘b’, that is where the concept of logarithm comes into the picture. You are asked for the value of ‘x’ such that a*a*a…. x (times) = b => x = Log  a  b This is also known as ‘ Log b to the base a’ ...