.png)
Introduction to Machine Learning
Machine Learning is buzzing around the world for the past few years, the reason for this is due to the high amount of data production, the increase of computation power and the development of better designs and algorithms.
If you decided to learn Machine Learning, you first need to learn and understand Linear Algebra. You may get surprised at why I am mentioning Linear Algebra. Let me explain to you...
The images & videos that we see daily or any data we see in Computer and mobile processors are 0's (Zero's) and 1's (One's) only.
Our face is represented by the matrix of Zero's and One's like a linear grouped in each matrix(pixel) of the image. Only then the mobile phone can recognize and authenticate for the use of your mobile. Unless it matches the matrix, the computer or mobile doesn't recognize you.
For Example:
Take 150 x 150 sized image - The computer reads it as 150 x 150 (rows x columns) matrix. 150px is just pixel size and contains value from 0-255 (2 power10)). If it is Black & White image - denoted in one matrix, for Multi-color Image - denoted in three matrix.
For Video(moving images), 1-second video = 24 fps (frames per second) so, 1 sec video contain 24 images.
To Analyse and prepare the work for machines, researchers created Neural Networks. It is similar to our brain functions. How Neurons think and give information about how things behave and work.
How our brain manipulates the data and takes decisions, Neural networks use the data and take decisions if it matches 33% or more. You may also encounter sometimes, face not recognized during Night (Darkness). But slowly it learns your face on different lights. You would get different experiences.
Mobile use Face Recognition by matching your face with various images using forward and backward propagation and recognize only based on the matrix.
Let's look into how these matrices are created/generated, how they get matched, rules and rules. To understand them, We need to learn Linear Algebra.
Machine Learning is used for automating mundane tasks to offering intelligent insights, industries in every sector try to benefit from it. You may already be using a device that utilizes it. For example, a wearable fitness tracker like Fitbit, or an intelligent home assistant like Alexa. But there are many more examples of ML in use.
Prediction — Machine learning can also be used in prediction systems. Considering the loan example, to compute the probability of a fault, the system will need to classify the available data in groups.
Image recognition — Machine learning can be used for face detection in an image as well. There is a separate category for each person in a database of several people.
Speech Recognition — It is the translation of spoken words into the text. It is used in voice searches and more. Voice user interfaces include voice dialing, call routing, and appliance control. It can also be used as simple data entry and the preparation of structured documents.
Medical diagnoses — ML is trained to recognize cancerous tissues.
The financial industry and trading — companies use ML in fraud investigations and credit checks.
According to Arthur Samuel, Machine Learning algorithms enable computers to learn from data, and even improve themselves, without being explicitly programmed.
Machine learning (ML) is a category of algorithm that allows software applications to become more accurate in predicting outcomes without being explicitly programmed.
Types of Machine Learning?
Machine learning can be classified into 4 types of algorithms.
Supervised Learning - [Link coming soon in a future blog]
Unsupervised Learning - [Link coming soon in a future blog]
Semi-Supervised Learning - [Link coming soon in a future blog]
Reinforcement Learning - [Link coming soon in a future blog]
We will see more about these various types of Machine learning in the next blog.
I hope you got something out of this blog. If you found this post illuminating at all, consider sharing this post and following for more upcoming content.