Original article was published on Deep Learning on Medium
A Quick Ride to Machine Learning
What is Machine Learning ?
Machine Learning (ML) is an area in computer science which involves teaching computers to do things naturally by learning through experience.This means that computer system is turning data into information.
Some Common Definitions
Nvidia defines Machine Learning as Machine Learning at its most basic is the practice of using algorithms to parse data , learn from it , and then make prediction about something in the world .
Stanford University defines it as Machine Learning is the science of getting computers to act without getting explicitly programmed.
Difference between AI , ML and DL
Many time you’ve been caught in the confusion of differentiating Artificial Intelligence(AI) , Machine Learning (ML) and Deep Learning (DL).
Although the three terminologies are usually used interchangeably, they do not quite refer to the same things.
We will clear this doubt in very simple words with example.
Artificial Intelligence :
AI means that the computer in one way or another way imitates human behaviour . It is purely math and scientific exercise.
- It includes planning,decision making,identifying objects,recognizing sound.
- It uses logic and decision trees.
- It includes ML.
Example : Driverless/Autonomous car.
Machine Learning :
- It is a subset of AI that contains method that allow computers to draw conclusions from data and provide them to AI application.
- It includes statistical models.
- Machine Improves with experience.
Example : Sales prediction by learning from sales data of past 2 months
Deep Learning :
- ML provides the desired output for the given input, but DL reads the input and applies it to another data.
- Deep Learning uses deep multi layered neural networks that functions like human brain neurons to classify images and give predictions.
- It is a technique for implementing Machine Learning.
Types of Machine Learning
- Supervised Machine Learning : In supervised machine learning the computer is provided with example inputs that are labeled with the desired outputs. Algorithms : Regression and Classification.
- Unsupervised Machine Learning : Here the data is unlabelled , so the learning algorithm is left to find commonalities among its input data. Algorithms : Clustering , Anomaly Detection , Association.
- Reinforcement Learning : Basically an AI where software agents ought to take action in an environment in order to get reward so that they improve. Example : Robot playing chess game.
How you can implement ML?
Some Programming Languages Used :
- Python – Because of short development time than any other languages python takes first place and its most used programming language in AI field.
- R – R is good for statistical purpose.
- Lisp – Lisp is one of the oldest and the most suited languages for the development in AI. It was invented by John McCarthy, the father of Artificial Intelligence in 1958.
- Prolog – This language stays alongside Lisp when we talk about development in AI field. The features provided by it include efficient pattern matching, tree-based data structuring and automatic backtracking.
- Java – Java provides many benefits: easy use, debugging ease, package services, simplified work with large-scale projects, graphical representation of data and better user interaction.
Some Frameworks Used :
1 . TensorFlow – A free platforms with APIs that help in buildng and training ML models.
2. Sci-kit Learn – It is one of the best ML frameworks for data mining and data analysis. It also supports models and algorithms.
3. PyTorch- With tons of option for optimizing algorithms, Torch is used to design neural networks using AutoGrad module and natural language processing.
Answer some questions before Landing
Do you know what is Machine Learning ?
Can you Differentiate between ML , AI and DL?
What are types of Machine Learning and frameworks used ?